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

    Neuronpedia

    INDEX
    Explanations

    implementation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     підс
    -0.07
     canal
    -0.07
    .tell
    -0.07
     vern
    -0.07
    ์โ
    -0.07
     Electoral
    -0.06
     weeds
    -0.06
    /ca
    -0.06
     cycle
    -0.06
    SGlobal
    -0.06
    POSITIVE LOGITS
    υπ
    0.07
     ihtiyaç
    0.06
     知
    0.06
     cảm
    0.06
    references
    0.06
    faf
    0.06
    ımızda
    0.06
    未
    0.06
    ======
    0.06
    BAB
    0.06
    Act Density 0.012%

    No Known Activations