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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -sn
    -0.07
    dsl
    -0.07
     λι
    -0.07
    czas
    -0.06
    Atl
    -0.06
     bullying
    -0.06
     helicopt
    -0.06
     زاده
    -0.06
    SU
    -0.06
    repositories
    -0.06
    POSITIVE LOGITS
     );
    0.07
    อส
    0.07
     přístup
    0.07
    ंस
    0.06
     illuminated
    0.06
     경험
    0.06
    х
    0.06
     casualties
    0.06
    ");
    0.06
    ErrorCode
    0.06
    Act Density 0.003%

    No Known Activations