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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thù
    -0.07
    婺
    -0.07
    ถาม
    -0.07
    layın
    -0.06
     pimp
    -0.06
    紧密结合
    -0.06
    珍惜
    -0.06
     rotterdam
    -0.06
    “(
    -0.06
    ился
    -0.06
    POSITIVE LOGITS
    _paper
    0.08
     obsolete
    0.07
    numberOf
    0.07
    Real
    0.07
    力还是自
    0.07
    Resultado
    0.06
     Processor
    0.06
    ♯
    0.06
    속
    0.06
     foolish
    0.06
    Act Density 0.046%

    No Known Activations