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

    Neuronpedia

    INDEX
    Explanations

    conditions, "on", and "given"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taboo
    -0.07
    .UserInfo
    -0.07
     Urdu
    -0.07
     Valk
    -0.07
    靶
    -0.07
    杵
    -0.07
     toc
    -0.07
    اعدة
    -0.07
     AdapterView
    -0.07
    _ends
    -0.07
    POSITIVE LOGITS
    湘西
    0.08
    
    0.07
    ➻
    0.07
    左
    0.07
    rices
    0.07
    \Entity
    0.07
    function
    0.07
    婚后
    0.07
     [[
    0.07
    =>
    0.07
    Act Density 0.006%

    No Known Activations