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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blers
    -0.07
    迷失
    -0.07
    bert
    -0.07
     profess
    -0.07
     Lê
    -0.07
     celebrates
    -0.07
     uncertainties
    -0.07
     erfahren
    -0.07
    Descricao
    -0.07
     clans
    -0.06
    POSITIVE LOGITS
     Больш
    0.07
    (Y
    0.07
    (base
    0.07
     bootstrap
    0.07
     match
    0.06
    对立
    0.06
    拍拍
    0.06
     Wordpress
    0.06
    �
    0.06
    (process
    0.06
    Act Density 0.019%

    No Known Activations