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

    Neuronpedia

    INDEX
    Explanations

    don

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     służb
    -0.07
    levelname
    -0.07
     трав
    -0.07
    <Response
    -0.07
     schw
    -0.07
     transf
    -0.07
     Southwest
    -0.06
    猶
    -0.06
    (Tag
    -0.06
     darling
    -0.06
    POSITIVE LOGITS
    ام
    0.07
     users
    0.07
    .descriptor
    0.07
     데이터
    0.07
    _WITH
    0.07
     mime
    0.07
     Mac
    0.07
     "";↵
    0.06
    rupted
    0.06
    /"
    0.06
    Act Density 0.002%

    No Known Activations