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

    Neuronpedia

    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "On
    -0.07
    _MEMORY
    -0.07
    (pro
    -0.07
    Death
    -0.07
     SOC
    -0.06
    ACH
    -0.06
    ap
    -0.06
    strength
    -0.06
    amac
    -0.06
    (PR
    -0.06
    POSITIVE LOGITS
    ूबर
    0.07
     کردند
    0.06
    や
    0.06
    blem
    0.06
     кры
    0.06
    =current
    0.06
    сы
    0.06
    bere
    0.06
     formulaire
    0.06
     unrestricted
    0.06
    Act Density 0.053%

    No Known Activations