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

    Neuronpedia

    INDEX
    Explanations

    say "size"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pattern
    -0.07
     Raider
    -0.07
    Startup
    -0.07
     products
    -0.07
    arsity
    -0.06
     spin
    -0.06
     Saint
    -0.06
     Little
    -0.06
     Fortune
    -0.06
     flatten
    -0.06
    POSITIVE LOGITS
    ПО
    0.07
    StepThrough
    0.06
    ])**
    0.06
    钮
    0.06
    plication
    0.06
    lineno
    0.06
    ceptar
    0.06
     несколь
    0.06
    datal
    0.06
    етич
    0.06
    Act Density 0.030%

    No Known Activations