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

    Neuronpedia

    INDEX
    Explanations

    tariff codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .warn
    -0.07
     harming
    -0.06
     privé
    -0.06
     pill
    -0.06
     Im
    -0.06
     가지
    -0.06
    (compare
    -0.06
     imposes
    -0.06
     Arbit
    -0.06
    ('*
    -0.06
    POSITIVE LOGITS
    煁
    0.08
    貅
    0.07
    צל
    0.07
    ####↵
    0.07
     Sharks
    0.07
    rece
    0.07
     stron
    0.06
    щей
    0.06
     Orleans
    0.06
    .";↵
    0.06
    Act Density 0.025%

    No Known Activations