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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    传
    -0.07
     advisory
    -0.07
     automobile
    -0.06
     اجر
    -0.06
     commented
    -0.06
     ents
    -0.06
     cuisine
    -0.06
     feminism
    -0.06
     finished
    -0.06
    .arc
    -0.06
    POSITIVE LOGITS
    @store
    0.07
     {*}
    0.07
    Intialized
    0.07
     حد
    0.06
    @Json
    0.06
     PYTHON
    0.06
    uitive
    0.06
    ��
    0.06
    //---------------------------------------------------------------------------↵↵
    0.06
    ,the
    0.06
    Act Density 0.299%

    No Known Activations