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

    Neuronpedia

    INDEX
    Explanations

    story excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jedn
    -0.07
     outs
    -0.06
    Combined
    -0.06
     oraz
    -0.06
     wicht
    -0.06
     Pes
    -0.06
     quarters
    -0.06
    uese
    -0.06
     barbecue
    -0.06
     worthwhile
    -0.06
    POSITIVE LOGITS
    LowerCase
    0.07
    \Message
    0.06
     alertController
    0.06
     sơn
    0.06
    _restore
    0.06
     자신의
    0.06
     >
    0.06
     accompanies
    0.06
    olet
    0.06
    _dns
    0.06
    Act Density 0.046%

    No Known Activations