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

    Neuronpedia

    INDEX
    Explanations

    say "hexadecimal"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    فة
    -0.07
    술
    -0.07
    alytics
    -0.07
    (Symbol
    -0.07
    ouden
    -0.06
    _spell
    -0.06
    idades
    -0.06
     finale
    -0.06
    ulation
    -0.06
    tre
    -0.06
    POSITIVE LOGITS
    ▍
    0.07
    anh
    0.06
    .getP
    0.06
     bakım
    0.06
     отсутств
    0.06
     اهد
    0.06
    ğmen
    0.06
     crist
    0.06
    appiness
    0.06
    _HEL
    0.06
    Act Density 0.049%

    No Known Activations