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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     आज
    -0.07
    ceans
    -0.07
     sellers
    -0.07
     Speaking
    -0.07
     joined
    -0.07
     в
    -0.06
    JKLMNOP
    -0.06
     mobile
    -0.06
     []);↵
    -0.06
     après
    -0.06
    POSITIVE LOGITS
    mi
    0.06
     解
    0.06
     Californ
    0.06
    oteric
    0.06
    .med
    0.06
    (orig
    0.05
     dataList
    0.05
    _probs
    0.05
     Folk
    0.05
    .CONNECT
    0.05
    Act Density 0.001%

    No Known Activations