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

    Neuronpedia

    INDEX
    Explanations

    Computer hardware and devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cambodia
    -0.08
    حار
    -0.07
     Mant
    -0.07
     Era
    -0.07
    _utils
    -0.07
     slid
    -0.07
     Â
    -0.07
     looked
    -0.07
    ,file
    -0.07
     שהם
    -0.07
    POSITIVE LOGITS
     פוסטים
    0.07
    .leave
    0.07
    łożyć
    0.07
     disciplinary
    0.07
    לין
    0.07
    벌
    0.06
    &)↵
    0.06
    posting
    0.06
    letal
    0.06
    landırma
    0.06
    Act Density 0.024%

    No Known Activations