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

    Neuronpedia

    INDEX
    Explanations

    complex language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doe
    -0.07
     komt
    -0.06
    rawing
    -0.06
    кус
    -0.06
     people
    -0.06
     Stanton
    -0.06
     exemple
    -0.06
     risking
    -0.06
    ,R
    -0.06
     expres
    -0.06
    POSITIVE LOGITS
     pacman
    0.07
    cdf
    0.06
     AsyncTask
    0.06
     Gig
    0.06
    ительных
    0.06
    afs
    0.06
     brill
    0.06
     assignable
    0.06
    _TEST
    0.06
    =id
    0.06
    Act Density 0.082%

    No Known Activations