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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    куль
    -0.07
    戰
    -0.07
    uristic
    -0.06
    alist
    -0.06
    atched
    -0.06
    Loss
    -0.06
     Presidential
    -0.06
    战
    -0.06
    ///↵
    -0.06
    む
    -0.06
    POSITIVE LOGITS
     formula
    0.06
     Yahoo
    0.06
     guarda
    0.06
     cracked
    0.06
     protr
    0.06
     pě
    0.06
     QTimer
    0.06
    xaa
    0.06
     martin
    0.06
    (Logger
    0.06
    Act Density 0.005%

    No Known Activations