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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lastly
    -0.07
    <object
    -0.06
    CUR
    -0.06
     allowance
    -0.06
     VI
    -0.06
    DESC
    -0.06
    reset
    -0.06
     naopak
    -0.06
     persecution
    -0.06
     Bakery
    -0.06
    POSITIVE LOGITS
    なん
    0.06
    ISH
    0.06
    ishes
    0.06
     五
    0.06
    σο
    0.06
    _utf
    0.06
     Trades
    0.06
     Λα
    0.06
     vocational
    0.06
     userEmail
    0.06
    Act Density 0.000%

    No Known Activations