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

    Neuronpedia

    INDEX
    Explanations

    actions and descriptions of movements or transformations

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

    Verbs of taking something off or putting it down

    np_acts-logits-general · gemini-2.0-flash

    physical actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.85
     Roskov
    -0.78
     beginnetje
    -0.74
    OGND
    -0.69
    setVerticalGroup
    -0.65
    InputBorder
    -0.65
    argout
    -0.63
    |}{}
    -0.62
    ⟬
    -0.60
     Réponses
    -0.60
    POSITIVE LOGITS
     cotone
    0.57
    ulescu
    0.52
     schweren
    0.50
    Feign
    0.48
     alluminio
    0.48
     herself
    0.47
    mpty
    0.46
    suchen
    0.46
     eût
    0.46
     penutup
    0.45
    Act Density 0.136%

    No Known Activations