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

    Neuronpedia

    INDEX
    Explanations

    arrest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bg
    -0.07
    arket
    -0.07
     varying
    -0.06
    /default
    -0.06
    Β
    -0.06
     pupils
    -0.06
     Javascript
    -0.06
    \Core
    -0.06
    /tool
    -0.06
     adaptable
    -0.06
    POSITIVE LOGITS
     коміс
    0.07
    Пос
    0.06
     κρα
    0.06
    بی
    0.06
    (prod
    0.06
    Damn
    0.06
    거
    0.06
     ober
    0.06
    날
    0.06
    Immediately
    0.06
    Act Density 0.019%

    No Known Activations