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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Independ
    -0.07
    Sample
    -0.07
    izens
    -0.07
     Ко
    -0.07
    cmp
    -0.07
    bye
    -0.07
    _budget
    -0.07
     imm
    -0.06
    افر
    -0.06
    (ap
    -0.06
    POSITIVE LOGITS
     Vice
    0.06
    .connector
    0.06
     Milan
    0.06
    ливих
    0.06
     Yahoo
    0.06
     Arguments
    0.06
     кг
    0.06
     neden
    0.06
    caling
    0.06
     silicon
    0.06
    Act Density 0.008%

    No Known Activations