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

    Neuronpedia

    INDEX
    Explanations

    literally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ох
    -0.07
     осві
    -0.07
    idential
    -0.06
    :disable
    -0.06
    Young
    -0.06
    CHO
    -0.06
    licted
    -0.06
     psycho
    -0.06
     Beste
    -0.06
    ايش
    -0.06
    POSITIVE LOGITS
     literally
    0.16
     """
↵
    0.07
     literal
    0.07
     루
    0.06
    perm
    0.06
    _LITERAL
    0.06
     Liter
    0.06
     фрукт
    0.06
    ataires
    0.06
    Liter
    0.06
    Act Density 0.002%

    No Known Activations