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

    Neuronpedia

    INDEX
    Explanations

    code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    İn
    -0.06
     متفاوت
    -0.06
    .i
    -0.06
    MarshalAs
    -0.06
     đỡ
    -0.06
     πρό
    -0.06
    Roman
    -0.06
     {↵↵↵↵
    -0.06
     entertainment
    -0.06
    [Boolean
    -0.06
    POSITIVE LOGITS
    яви
    0.07
     McCoy
    0.06
    "data
    0.06
    ुब
    0.06
     […]↵↵
    0.06
    �
    0.06
    ":"
    0.06
     "")
↵
    0.06
    elsey
    0.06
    }->
    0.06
    Act Density 0.108%

    No Known Activations