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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoops
    -0.06
     Boone
    -0.06
     approvals
    -0.06
    ดาว
    -0.06
     однако
    -0.06
    anguage
    -0.06
     conseils
    -0.06
    cles
    -0.06
     ông
    -0.06
    minated
    -0.06
    POSITIVE LOGITS
     sistema
    0.07
    955
    0.07
    _Button
    0.07
     @{$
    0.06
    Χ
    0.06
    _CORE
    0.06
     LSTM
    0.06
    .Std
    0.06
    async
    0.06
     whiteColor
    0.06
    Act Density 0.000%

    No Known Activations