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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prepared
    -0.07
    (include
    -0.06
    resolver
    -0.06
    发
    -0.06
    ThreadPool
    -0.06
    �
    -0.06
    _segments
    -0.06
    Dani
    -0.06
     Brighton
    -0.06
    라
    -0.06
    POSITIVE LOGITS
     carta
    0.07
     Shank
    0.07
    mızı
    0.07
    .Rest
    0.06
    .IM
    0.06
    ısıt
    0.06
    าตร
    0.06
     radar
    0.06
    .MONTH
    0.06
    .Id
    0.06
    Act Density 0.015%

    No Known Activations