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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    common
    -0.06
    Tyler
    -0.06
     Anal
    -0.06
     hypocrisy
    -0.06
    慎
    -0.06
     �
    -0.06
     жод
    -0.06
    こ
    -0.06
     yoluyla
    -0.06
    étique
    -0.06
    POSITIVE LOGITS
    يع
    0.06
     explo
    0.06
    .Tasks
    0.06
    geb
    0.06
     ук
    0.06
    emez
    0.06
     мет
    0.06
    ante
    0.06
    )}>
    0.06
    нов
    0.06
    Act Density 0.000%

    No Known Activations