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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spar
    -0.07
     FS
    -0.07
     elektr
    -0.06
     sup
    -0.06
     sincerity
    -0.06
     sof
    -0.06
     EXISTS
    -0.06
    elidir
    -0.06
     flips
    -0.06
     flaw
    -0.06
    POSITIVE LOGITS
    ymbol
    0.07
    versed
    0.07
     gambling
    0.06
    伤
    0.06
    layıcı
    0.06
    (EC
    0.06
    (er
    0.06
     thẻ
    0.06
    ource
    0.06
     çıkan
    0.06
    Act Density 0.007%

    No Known Activations