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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Diagonal
    -0.08
     flog
    -0.08
     અટ
    -0.08
     fruct
    -0.07
     પાસે
    -0.07
     સુંદર
    -0.07
     બચ
    -0.07
    .Generic
    -0.07
     arrêt
    -0.07
     nghe
    -0.07
    POSITIVE LOGITS
    ，与
    0.08
    后的
    0.07
     relatif
    0.07
     المو
    0.07
    到账
    0.07
    rement
    0.07
    /+
    0.07
     verkrijgen
    0.07
    /A
    0.07
    。↵↵
    0.07
    Act Density 0.062%

    No Known Activations