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

    Neuronpedia

    INDEX
    Explanations

    relates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    luž
    -0.07
     WebElement
    -0.07
     Profiles
    -0.07
     translations
    -0.06
    ยน
    -0.06
     Neu
    -0.06
     injections
    -0.06
    checkbox
    -0.06
    )</
    -0.06
    (car
    -0.06
    POSITIVE LOGITS
    .neo
    0.06
    eyi
    0.06
    rebbe
    0.06
    ामल
    0.06
    zeigt
    0.06
    ogi
    0.06
    _ENV
    0.06
     Fasc
    0.06
    _substr
    0.06
     katıl
    0.06
    Act Density 0.008%

    No Known Activations