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

    Neuronpedia

    INDEX
    Explanations

    hashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $sub
    -0.08
     fuss
    -0.07
    �
    -0.07
     contrato
    -0.07
    δά
    -0.07
    今天
    -0.06
    ^\
    -0.06
    -agent
    -0.06
     واحدة
    -0.06
    abouts
    -0.06
    POSITIVE LOGITS
     initiating
    0.09
     opportunity
    0.07
     Kenn
    0.07
     Ellen
    0.07
     illicit
    0.07
    sequently
    0.06
     Solomon
    0.06
     decorating
    0.06
     Threat
    0.06
    Scott
    0.06
    Act Density 0.002%

    No Known Activations