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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     रहता
    -0.08
    ्भ
    -0.08
     Protección
    -0.08
     результата
    -0.08
     همیشه
    -0.08
    违规
    -0.07
     Balanced
    -0.07
     uvijek
    -0.07
    uchenget
    -0.07
     machining
    -0.07
    POSITIVE LOGITS
     dismant
    0.11
     reforms
    0.10
     commun
    0.10
     neoliberal
    0.09
     collapse
    0.09
    -collapse
    0.09
     repeal
    0.09
     unleash
    0.09
     easing
    0.09
     emancip
    0.09
    Act Density 0.013%

    No Known Activations