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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seinen
    -0.08
    alsex
    -0.07
    REL
    -0.07
    렌
    -0.07
    わり
    -0.07
    cluir
    -0.07
    ">'+
    -0.06
    _charset
    -0.06
     prohibition
    -0.06
    osp
    -0.06
    POSITIVE LOGITS
    \xe
    0.07
    జ
    0.06
     недо
    0.06
    Ү
    0.06
    骠
    0.06
    _ud
    0.06
    מט
    0.06
    .rmtree
    0.06
    Fine
    0.06
    toBeDefined
    0.06
    Act Density 0.005%

    No Known Activations