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

    Neuronpedia

    INDEX
    Explanations

    deals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ificado
    -0.07
     gun
    -0.07
     листь
    -0.07
    MEMORY
    -0.07
    ...'
    -0.07
     rightly
    -0.06
    bullet
    -0.06
    ocre
    -0.06
    )"
    -0.06
    ными
    -0.06
    POSITIVE LOGITS
    chner
    0.07
     申博
    0.07
    قط
    0.06
    _tip
    0.06
    _MAIL
    0.06
    drawer
    0.06
     Bund
    0.06
    lik
    0.06
     σχ
    0.06
     proves
    0.06
    Act Density 0.007%

    No Known Activations