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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vodka
    -0.06
    ')}}"
    -0.06
     bột
    -0.06
     боя
    -0.06
     chickens
    -0.06
    ム
    -0.06
    queued
    -0.06
     eleven
    -0.06
    ]['
    -0.06
    '];?></
    -0.06
    POSITIVE LOGITS
     ребенка
    0.07
     Obj
    0.06
    OMBRE
    0.06
     ک
    0.06
                        ↵
    0.06
    ै?
    0.06
    axe
    0.06
    ินเด
    0.06
    .Big
    0.06
     acronym
    0.06
    Act Density 0.022%

    No Known Activations