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

    Neuronpedia

    INDEX
    Explanations

    choices and candidates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    済
    -0.07
     visite
    -0.07
    арч
    -0.06
     Inhal
    -0.06
     Basics
    -0.06
     Heads
    -0.06
    แจ
    -0.06
     Tata
    -0.06
    レビ
    -0.06
     Carly
    -0.06
    POSITIVE LOGITS
     hailed
    0.06
     SERVICES
    0.06
     why
    0.06
     YM
    0.06
    flen
    0.06
     Why
    0.06
    Open
    0.06
    Why
    0.06
     []↵↵↵
    0.06
     snaps
    0.06
    Act Density 0.092%

    No Known Activations