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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etu
    -0.07
    icus
    -0.07
     ISPs
    -0.06
    Debe
    -0.06
     المن
    -0.06
    _MON
    -0.06
    -mon
    -0.06
    _"+
    -0.06
    .AspNet
    -0.06
     vim
    -0.06
    POSITIVE LOGITS
    2
    0.08
    音
    0.06
    ฑ
    0.06
    Away
    0.06
    [:
    0.06
    phys
    0.06
    าท
    0.06
    ált
    0.06
    cloak
    0.06
    اده
    0.06
    Act Density 0.018%

    No Known Activations