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

    Neuronpedia

    INDEX
    Explanations

    phrases that include references to specific contributions or aspects

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

    in part by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.67
    SharedCtor
    -0.60
     MainAxisSize
    -0.59
     createSprite
    -0.57
    RenderAtEndOf
    -0.55
     Infórmanos
    -0.54
     للمعارف
    -0.54
     henvisninger
    -0.54
    ✨:
    -0.53
     avoient
    -0.53
    POSITIVE LOGITS
     part
    0.91
     partly
    0.90
     Partly
    0.82
     partially
    0.81
    Partly
    0.78
     Part
    0.75
    partly
    0.74
    part
    0.74
    Part
    0.72
     Partially
    0.72
    Act Density 0.015%

    No Known Activations