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

    Neuronpedia

    INDEX
    Explanations

    scientific experimental procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     año
    -0.07
    manship
    -0.07
     навіть
    -0.07
     usuario
    -0.06
     hacks
    -0.06
    (static
    -0.06
    adı
    -0.06
     еще
    -0.06
    　 　 　
    -0.06
     vlády
    -0.06
    POSITIVE LOGITS
     recycled
    0.07
    δη
    0.06
    -Mar
    0.06
    .languages
    0.06
    //----------------------------------------------------------------------------↵
    0.06
    .priv
    0.06
    vip
    0.06
     PH
    0.06
     Elis
    0.06
    );">↵
    0.06
    Act Density 0.078%

    No Known Activations