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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IÓN
    -0.07
     Numero
    -0.07
    solver
    -0.07
    -making
    -0.06
    iação
    -0.06
    ежду
    -0.06
     shape
    -0.06
    izyon
    -0.06
    icals
    -0.06
    ്�
    -0.06
    POSITIVE LOGITS
     мо
    0.06
     TextStyle
    0.06
     collisions
    0.06
    �
    0.06
     dealing
    0.06
    ATO
    0.06
     совсем
    0.06
     خودش
    0.06
     згод
    0.06
    ]=(
    0.06
    Act Density 0.007%

    No Known Activations