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

    Neuronpedia

    INDEX
    Explanations

    contrasting phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     JsonObject
    -0.07
    ада
    -0.06
     pipelines
    -0.06
    DataTable
    -0.06
    553
    -0.06
    Cho
    -0.06
    esine
    -0.06
    Allocate
    -0.06
    variant
    -0.06
    POSITIVE LOGITS
     anime
    0.07
    爱
    0.06
     신청
    0.06
    _skills
    0.06
     爱
    0.06
     Wizards
    0.06
    чає
    0.06
     luyện
    0.06
    embers
    0.06
     ￥
    0.06
    Act Density 0.171%

    No Known Activations