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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    COME
    -0.07
    kode
    -0.07
    69
    -0.06
     어�
    -0.06
     Clear
    -0.06
    弃
    -0.06
     True
    -0.06
    468
    -0.06
    MOD
    -0.06
    Pie
    -0.06
    POSITIVE LOGITS
    worker
    0.07
     дал
    0.07
    _child
    0.06
     Probe
    0.06
     ForCanBeConvertedToForeach
    0.06
    _Size
    0.06
     withdrawing
    0.06
     Warfare
    0.06
     Dani
    0.06
    endpoint
    0.06
    Act Density 0.018%

    No Known Activations