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

    Neuronpedia

    INDEX
    Explanations

    WTF or f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    北海道
    -0.08
    eloze
    -0.08
    fog
    -0.08
    سسات
    -0.08
    pd
    -0.08
    iço
    -0.08
     gur
    -0.08
     لا
    -0.08
     اب
    -0.07
     {}
    -0.07
    POSITIVE LOGITS
    ୀ
    0.08
     Rif
    0.08
     intelect
    0.08
     FI
    0.08
     Miche
    0.07
     moindre
    0.07
    ению
    0.07
     vorhanden
    0.07
     GG
    0.07
     Fer
    0.07
    Act Density 0.001%

    No Known Activations