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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    告诉大家
    -0.08
    וביל
    -0.08
    外套
    -0.07
     nouvel
    -0.07
     nội
    -0.07
     Harr
    -0.07
    .replace
    -0.07
    _sdk
    -0.07
    运用
    -0.06
    🐻
    -0.06
    POSITIVE LOGITS
     Suicide
    0.07
    コスト
    0.07
    _First
    0.06
     offsets
    0.06
     Yorkers
    0.06
     Devils
    0.06
     PATCH
    0.06
    �
    0.06
    �
    0.06
    .Repositories
    0.06
    Act Density 0.004%

    No Known Activations