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

    Neuronpedia

    INDEX
    Explanations

    identification numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Preston
    -0.07
     Naz
    -0.07
     Kan
    -0.07
    ーナ
    -0.07
    _ar
    -0.06
    ghan
    -0.06
    Sol
    -0.06
    の
    -0.06
     �
    -0.06
     Yad
    -0.06
    POSITIVE LOGITS
    (card
    0.07
     scrimmage
    0.07
     atop
    0.07
     канди
    0.07
    stantial
    0.06
     facile
    0.06
    İstanbul
    0.06
     Colum
    0.06
    ::::/
    0.06
     quay
    0.06
    Act Density 0.014%

    No Known Activations