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

    Neuronpedia

    INDEX
    Explanations

    Foreign words/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NW
    -0.07
     VM
    -0.07
    962
    -0.07
    'T
    -0.07
    First
    -0.07
    neği
    -0.06
    FRINGEMENT
    -0.06
    -C
    -0.06
    forum
    -0.06
     CFO
    -0.06
    POSITIVE LOGITS
     περ
    0.07
    (rad
    0.07
    _gchandle
    0.07
    _MODULES
    0.06
    .LogError
    0.06
     individ
    0.06
    "].(
    0.06
    (IService
    0.06
    (?:
    0.06
     totalmente
    0.06
    Act Density 0.019%

    No Known Activations