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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โปร
    -0.08
    heat
    -0.07
    机会
    -0.07
    .initializeApp
    -0.07
    春风
    -0.07
    Looks
    -0.07
    циально
    -0.07
    借此
    -0.07
    PullParser
    -0.07
    וח
    -0.07
    POSITIVE LOGITS
    .matrix
    0.07
     미
    0.07
    瘀
    0.07
     "\"
    0.07
     cad
    0.07
    万余
    0.07
    🇳
    0.07
     petty
    0.07
    ATA
    0.06
     것을
    0.06
    Act Density 0.005%

    No Known Activations