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

    Neuronpedia

    INDEX
    Explanations

    say capitalized place names/abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grado
    -0.07
    Inicio
    -0.07
    step
    -0.07
    forall
    -0.07
    _days
    -0.06
     mort
    -0.06
     Cele
    -0.06
     Bret
    -0.06
    .ACT
    -0.06
     Mons
    -0.06
    POSITIVE LOGITS
    مي
    0.07
    ombat
    0.06
    .URL
    0.06
     hamburger
    0.06
    yling
    0.06
     شبکه
    0.06
    gregate
    0.06
    ARC
    0.06
    ��
    0.06
     Century
    0.06
    Act Density 0.014%

    No Known Activations