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

    Neuronpedia

    INDEX
    Explanations

    terms related to acquisition, learning, and behavior development

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

    learned acquired inherited choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.83
    RenderAtEndOf
    -0.82
     ProtoMessage
    -0.79
     GenerationType
    -0.73
    PerformLayout
    -0.73
     ब्रेकडाउन
    -0.73
    WithIOException
    -0.72
    EndContext
    -0.69
     BoxFit
    -0.69
     Chwiliwch
    -0.67
    POSITIVE LOGITS
     earned
    0.44
    earned
    0.43
    Inherited
    0.40
     Earned
    0.37
    editary
    0.36
     inherited
    0.36
    learned
    0.35
    analyze
    0.33
    shared
    0.33
    eux
    0.33
    Act Density 0.236%

    No Known Activations