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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TValue
    -0.08
    /themes
    -0.07
     Владимир
    -0.07
    答え
    -0.07
    🐢
    -0.07
    .valid
    -0.06
    getContent
    -0.06
    ธร
    -0.06
    תכנון
    -0.06
     tolua
    -0.06
    POSITIVE LOGITS
     pst
    0.07
    晕
    0.07
    七年
    0.07
    离去
    0.06
     Iranian
    0.06
     tặng
    0.06
    ofs
    0.06
     vitro
    0.06
    systems
    0.06
    一旦
    0.06
    Act Density 0.031%

    No Known Activations