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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แขน
    -0.07
     NotImplementedException
    -0.07
     Surely
    -0.07
     UserID
    -0.07
    én
    -0.07
     образования
    -0.07
    _enc
    -0.07
    典范
    -0.06
    ניסיון
    -0.06
     mö
    -0.06
    POSITIVE LOGITS
    平坦
    0.08
     tops
    0.07
    ⵟ
    0.07
    谷
    0.07
    @@@@
    0.07
    稃
    0.07
    喷涂
    0.07
    �
    0.07
     refined
    0.06
    ตาร
    0.06
    Act Density 0.029%

    No Known Activations