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

    Neuronpedia

    INDEX
    Explanations

    .HashMap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     jsonify
    -0.07
     exploitation
    -0.07
    ikh
    -0.07
    Ax
    -0.06
    :-
    -0.06
     fruits
    -0.06
     tiểu
    -0.06
    於
    -0.06
    屬於
    -0.06
    POSITIVE LOGITS
    %;">
    0.07
    鲺
    0.07
    벰
    0.07
    ᑖ
    0.06
    рам
    0.06
    谰
    0.06
    媸
    0.06
    ;',
    0.06
     incoming
    0.06
    文化建设
    0.06
    Act Density 0.002%

    No Known Activations