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

    Neuronpedia

    INDEX
    Explanations

    inent/prominent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mod
    -0.07
     adj
    -0.07
    缅
    -0.07
     mediated
    -0.07
    فئة
    -0.07
    aso
    -0.07
     обы
    -0.07
    ((
    -0.07
    <Box
    -0.07
    ﰃ
    -0.07
    POSITIVE LOGITS
    公元前
    0.08
    …it
    0.08
     Confirmation
    0.07
    utm
    0.07
    始终坚持
    0.07
    okemon
    0.07
    能够
    0.07
    状元
    0.07
     véritable
    0.07
    早就
    0.07
    Act Density 0.006%

    No Known Activations