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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    repr
    -0.07
    (pic
    -0.06
    Snippet
    -0.06
    ()<
    -0.06
     平
    -0.06
    itat
    -0.06
     TEN
    -0.06
    518
    -0.06
     Maz
    -0.05
     sensors
    -0.05
    POSITIVE LOGITS
     nabí
    0.07
    .astype
    0.07
     Độ
    0.07
    .experimental
    0.06
     ауд
    0.06
    ении
    0.06
    웃
    0.06
     bombed
    0.06
    кових
    0.06
     Ông
    0.06
    Act Density 0.251%

    No Known Activations