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

    Neuronpedia

    INDEX
    Explanations

    coding software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .functions
    -0.06
    aced
    -0.06
     新
    -0.06
    confirmed
    -0.06
     住
    -0.06
     Reading
    -0.06
    /basic
    -0.06
    耐
    -0.06
    外
    -0.06
     notoriously
    -0.05
    POSITIVE LOGITS
     Aleppo
    0.09
     öz
    0.07
    NEY
    0.07
    �
    0.07
    ्वप
    0.07
     sécur
    0.06
    ESIS
    0.06
    otton
    0.06
    lament
    0.06
    orney
    0.06
    Act Density 0.081%

    No Known Activations