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

    Neuronpedia

    INDEX
    Explanations

    code operator precedence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     средство
    -0.07
     vždy
    -0.07
     мере
    -0.06
     pourquoi
    -0.06
    ,_
    -0.06
     WHICH
    -0.06
     grace
    -0.06
     anda
    -0.06
     hodnocení
    -0.06
    —which
    -0.06
    POSITIVE LOGITS
    ookies
    0.06
    alleng
    0.06
     affirmative
    0.06
     Event
    0.06
     Largest
    0.06
    ／↵
    0.06
     siyasi
    0.06
    -Regular
    0.05
    ALTER
    0.05
    .frames
    0.05
    Act Density 0.036%

    No Known Activations