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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mitochondrial
    -0.08
     Cosmos
    -0.07
    .NoArgsConstructor
    -0.07
     trio
    -0.07
     Primer
    -0.07
    شي
    -0.07
    aldo
    -0.06
     Humans
    -0.06
     Norris
    -0.06
     guy
    -0.06
    POSITIVE LOGITS
    eguard
    0.06
     Lana
    0.06
    �
    0.06
    атора
    0.06
     آزمایش
    0.06
     판매
    0.06
     {
↵
↵
↵
    0.06
    ................
    0.06
    ,min
    0.06
     Прав
    0.06
    Act Density 0.136%

    No Known Activations