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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tit
    -0.06
    SPEC
    -0.06
    QRST
    -0.06
    Dans
    -0.06
     thems
    -0.06
     حساب
    -0.06
     Bloc
    -0.06
    Indexed
    -0.06
    _PS
    -0.06
    학년
    -0.06
    POSITIVE LOGITS
     gun
    0.06
    (tree
    0.06
    も
    0.06
    —but
    0.06
     highlighting
    0.06
    нее
    0.06
     있었다
    0.06
     Enums
    0.06
     YY
    0.05
     proclaimed
    0.05
    Act Density 0.005%

    No Known Activations