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

    Neuronpedia

    INDEX
    Explanations

    antivirus software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Στα
    -0.07
     Severity
    -0.06
    .vertx
    -0.06
     dů
    -0.06
     одне
    -0.06
     shard
    -0.06
     aime
    -0.06
     zpráva
    -0.06
     Peb
    -0.06
     callers
    -0.06
    POSITIVE LOGITS
     süt
    0.07
    Constant
    0.07
     stretching
    0.06
    licated
    0.06
    ires
    0.06
    литель
    0.06
     uncon
    0.06
     DU
    0.06
     등
    0.06
     истории
    0.06
    Act Density 0.003%

    No Known Activations