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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alarming
    -0.07
    $PostalCodesNL
    -0.07
     conform
    -0.06
     format
    -0.06
    detail
    -0.06
     message
    -0.06
     fog
    -0.06
    Whats
    -0.06
    HIGH
    -0.06
     BOOLEAN
    -0.06
    POSITIVE LOGITS
    iệt
    0.08
    oredProcedure
    0.07
    erving
    0.07
     Interactive
    0.07
    iglia
    0.07
    -contrib
    0.07
    -mult
    0.06
     Fighters
    0.06
    ders
    0.06
    GetProperty
    0.06
    Act Density 0.039%

    No Known Activations