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

    Neuronpedia

    INDEX
    Explanations

    Towns and administrative divisions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _padding
    -0.07
    /python
    -0.07
     workers
    -0.07
    _reward
    -0.07
    _value
    -0.07
     Rack
    -0.07
    ูล
    -0.07
     Psychology
    -0.06
     produce
    -0.06
    ctx
    -0.06
    POSITIVE LOGITS
     Sabb
    0.06
    ');?>"
    0.06
    _mod
    0.06
     पड़
    0.06
    +r
    0.06
     cof
    0.06
    图片
    0.05
    .SimpleDateFormat
    0.05
     इसम
    0.05
     repreh
    0.05
    Act Density 0.014%

    No Known Activations