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

    Neuronpedia

    INDEX
    Explanations

    job titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strings
    -0.07
     valores
    -0.06
     sleepy
    -0.06
    ください
    -0.06
    ennon
    -0.06
     fictional
    -0.06
    xfe
    -0.06
    ику
    -0.06
    _cliente
    -0.06
    ower
    -0.06
    POSITIVE LOGITS
    .SQLException
    0.08
     meas
    0.07
     письмен
    0.07
     пенс
    0.06
     mev
    0.06
     photograph
    0.06
    /********************************
    0.06
     sim
    0.06
    hl
    0.06
     Burb
    0.06
    Act Density 0.031%

    No Known Activations