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

    Neuronpedia

    INDEX
    Explanations

    code libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �니다
    -0.07
     Better
    -0.07
    赠
    -0.07
    졍
    -0.06
    _Act
    -0.06
    /maps
    -0.06
    没收
    -0.06
     được
    -0.06
     offence
    -0.06
     Mus
    -0.06
    POSITIVE LOGITS
    _LEVEL
    0.07
    .qq
    0.07
    ocation
    0.07
    Invocation
    0.07
     roughly
    0.07
    (track
    0.07
    รอบ
    0.07
    ไกล
    0.07
     созд
    0.07
    Hooks
    0.06
    Act Density 0.009%

    No Known Activations