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
     ordinary
    -0.07
     разд
    -0.07
    something
    -0.07
    unicorn
    -0.07
    espoň
    -0.07
    manı
    -0.06
     classics
    -0.06
     */
    -0.06
    .ca
    -0.06
    ulle
    -0.06
    POSITIVE LOGITS
     lumber
    0.07
    -к
    0.06
     अब
    0.06
     SQ
    0.06
    oglob
    0.06
     Surv
    0.06
     invokevirtual
    0.06
    ega
    0.06
     abdom
    0.06
    ريقة
    0.06
    Act Density 0.101%

    No Known Activations