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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Posted
    -0.07
    .header
    -0.07
    afari
    -0.07
    In
    -0.06
    ipients
    -0.06
     فريق
    -0.06
    <l
    -0.06
    -up
    -0.06
    .flex
    -0.06
     today
    -0.06
    POSITIVE LOGITS
    .emplace
    0.06
     trừ
    0.06
    �
    0.06
     vac
    0.06
    -testid
    0.06
    _RULE
    0.06
     yeniden
    0.06
     вокруг
    0.06
    σχ
    0.06
    گان
    0.06
    Act Density 0.048%

    No Known Activations