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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    电影
    -0.08
    Display
    -0.07
    "My
    -0.07
    (Throwable
    -0.07
    _Params
    -0.06
     Laravel
    -0.06
    _IC
    -0.06
    лаш
    -0.06
     мист
    -0.06
     Lenovo
    -0.06
    POSITIVE LOGITS
     propagated
    0.06
     champ
    0.06
    -aut
    0.06
     erf
    0.06
    iker
    0.06
     CHtml
    0.06
    _beam
    0.06
    PerPage
    0.06
     ダ
    0.06
     shortened
    0.06
    Act Density 0.071%

    No Known Activations