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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "{\"
    -0.07
    .NoError
    -0.07
    .Storage
    -0.07
     "{}
    -0.06
     Leading
    -0.06
    .weixin
    -0.06
    (hour
    -0.06
     boxShadow
    -0.06
    stringValue
    -0.06
    accel
    -0.06
    POSITIVE LOGITS
     bah
    0.07
    ecial
    0.06
     متن
    0.06
     Nh
    0.06
    рат
    0.06
     dokun
    0.06
     try
    0.06
     itens
    0.06
     boot
    0.06
    をする
    0.06
    Act Density 0.015%

    No Known Activations