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

    Neuronpedia

    INDEX
    Explanations

    say "un" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASSWORD
    -0.06
    324
    -0.06
    Council
    -0.06
     zur
    -0.06
     respuesta
    -0.06
     retirement
    -0.06
     rift
    -0.06
     rad
    -0.06
     rotates
    -0.06
    .Tables
    -0.06
    POSITIVE LOGITS
    روض
    0.08
    šil
    0.07
    สถ
    0.07
    ulmuş
    0.07
    ضو
    0.07
    aguay
    0.07
    имер
    0.06
    ible
    0.06
     threadIdx
    0.06
    审
    0.06
    Act Density 0.001%

    No Known Activations