Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs and phrases indicating actions or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "How to" instructions or questions

    np_acts-logits-general · gemini-2.0-flash

    explaining how to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.67
     asupra
    -0.61
    Hauptartikel
    -0.60
    WebVitals
    -0.59
    ThroughAttribute
    -0.58
    SequentialGroup
    -0.56
    readFileSync
    -0.56
    invokeLater
    -0.55
     [*]
    -0.54
     constater
    -0.53
    POSITIVE LOGITS
     best
    1.04
     properly
    1.03
     safely
    0.93
    properly
    0.87
    best
    0.80
     approach
    0.80
     effectively
    0.79
     correctly
    0.76
     deal
    0.75
     PROPER
    0.73
    Act Density 0.204%

    No Known Activations