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

    Neuronpedia

    INDEX
    Explanations

    onPressed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    送
    -0.07
     müdür
    -0.06
    ,args
    -0.06
    masını
    -0.06
     klas
    -0.06
    (stats
    -0.06
    chnitt
    -0.06
     scriptures
    -0.06
    interp
    -0.06
    trfs
    -0.06
    POSITIVE LOGITS
     onPressed
    0.11
     TOD
    0.07
     GM
    0.07
    vant
    0.07
    .Th
    0.07
     fark
    0.07
     formulation
    0.07
     tap
    0.07
    During
    0.07
     Cot
    0.07
    Act Density 0.001%

    No Known Activations