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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Entire
    -0.08
    ใหม
    -0.07
    ysl
    -0.07
    .ret
    -0.06
    ayo
    -0.06
     Blade
    -0.06
    esinde
    -0.06
     ha
    -0.06
    ｜
    -0.06
    .eval
    -0.06
    POSITIVE LOGITS
     bisexual
    0.08
     intuitive
    0.07
     attempted
    0.06
     Sharon
    0.06
    (cv
    0.06
    aigned
    0.06
     Directed
    0.06
    علومات
    0.06
     consulted
    0.06
     principalTable
    0.06
    Act Density 0.003%

    No Known Activations