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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating knowledge or competence in a subject

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

    what is going on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.39
    ſelves
    -0.39
    ########.
    -0.38
    InjectAttribute
    -0.37
    Portail
    -0.37
    Vaata
    -0.35
    argout
    -0.34
    Aiheesta
    -0.33
    :✨
    -0.32
     ře
    -0.32
    POSITIVE LOGITS
     nahilalakip
    0.55
     onBind
    0.50
     Adequate
    0.50
    sapato
    0.49
    handling
    0.49
     Awareness
    0.47
    arraycopy
    0.47
    declaration
    0.47
    ruly
    0.46
    TITUDE
    0.46
    Act Density 0.020%

    No Known Activations