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

    Neuronpedia

    INDEX
    Explanations

    Accidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gains
    -0.08
    øm
    -0.07
    -0.07
    PG
    -0.07
     miteinander
    -0.07
    oki
    -0.07
    eng
    -0.07
     már
    -0.07
     sharper
    -0.07
    pg
    -0.07
    POSITIVE LOGITS
     справа
    0.08
     mummy
    0.08
    withstanding
    0.08
     Confidential
    0.08
     independiente
    0.08
     respectivos
    0.08
     xuyên
    0.08
     tomates
    0.08
     Independent
    0.08
     personalmente
    0.07
    Act Density 0.008%
    No Known Activations