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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals seeking help with shared problems

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

    learning and future reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.72
    RTGC
    -0.46
    LabelTagHelper
    -0.42
     transfieras
    -0.42
    awtextra
    -0.41
    toMatchSnapshot
    -0.41
     Inflate
    -0.40
    cyklopedia
    -0.40
    MessageTagHelper
    -0.40
    paramref
    -0.39
    POSITIVE LOGITS
     pitié
    0.51
     kaarangay
    0.48
    Trevor
    0.45
    ostante
    0.44
    quisa
    0.43
     Trevor
    0.41
     София
    0.39
     Meksiko
    0.39
    反正
    0.39
     referenties
    0.39
    Act Density 0.068%

    No Known Activations