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

    Neuronpedia

    INDEX
    Explanations

    say "STR word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sb
    -0.06
    .itemView
    -0.06
     seizure
    -0.06
    адж
    -0.06
    /{
    -0.06
     yc
    -0.06
    .no
    -0.06
    .writeString
    -0.06
     Cats
    -0.06
    .with
    -0.06
    POSITIVE LOGITS
     большой
    0.06
     Hanging
    0.06
    ph
    0.06
    _Display
    0.06
    -ce
    0.06
     cantidad
    0.06
    BOOST
    0.06
     earlier
    0.06
     hurting
    0.06
    ErrorException
    0.06
    Act Density 0.001%

    No Known Activations