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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    に基
    -0.07
    浍
    -0.07
    てくる
    -0.07
    _->
    -0.07
    quipe
    -0.07
    ="#">
    -0.06
    走进
    -0.06
     каждой
    -0.06
    していく
    -0.06
     שהם
    -0.06
    POSITIVE LOGITS
    ihilation
    0.07
     muzzle
    0.07
     Achievement
    0.07
    Platforms
    0.07
     Bürger
    0.07
    铺
    0.07
    .Output
    0.06
    🔞
    0.06
     filter
    0.06
     WARNING
    0.06
    Act Density 0.021%

    No Known Activations