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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disgrace
    -0.06
    .ApplyResources
    -0.06
    .getOwnPropertyDescriptor
    -0.06
    istles
    -0.06
     Що
    -0.06
     Scouts
    -0.06
    งส
    -0.06
    題
    -0.06
    <Transform
    -0.06
     Constant
    -0.06
    POSITIVE LOGITS
     American
    0.06
     міжнарод
    0.06
     吉
    0.06
    olla
    0.06
    ゴ
    0.06
    tic
    0.06
     nákup
    0.06
    (od
    0.06
     спіл
    0.06
     natural
    0.06
    Act Density 0.005%

    No Known Activations