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

    Neuronpedia

    INDEX
    Explanations

    prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     positivity
    -0.06
    _chi
    -0.06
    CMD
    -0.06
    و
    -0.06
     scalp
    -0.06
     scaffold
    -0.06
     switches
    -0.06
     Choices
    -0.06
    not
    -0.06
     вступ
    -0.06
    POSITIVE LOGITS
    弄
    0.07
    setDefault
    0.07
     ürünleri
    0.07
     �
    0.07
     production
    0.06
     disabilities
    0.06
    数量
    0.06
     период
    0.06
     sensible
    0.06
     Workspace
    0.06
    Act Density 0.001%

    No Known Activations