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

    Neuronpedia

    INDEX
    Explanations

    something at stake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    740
    -0.07
    -validator
    -0.06
    Assets
    -0.06
    Stack
    -0.06
     Moder
    -0.06
    locator
    -0.06
    .Logging
    -0.06
    492
    -0.06
    "E
    -0.06
     stupidity
    -0.06
    POSITIVE LOGITS
    .plist
    0.07
     delic
    0.07
    /L
    0.07
     نسبة
    0.06
     dismantle
    0.06
     procent
    0.06
     đề
    0.06
    .MON
    0.06
     pione
    0.06
    _TRIGGER
    0.06
    Act Density 0.038%

    No Known Activations