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

    Neuronpedia

    INDEX
    Explanations

    conditioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     можливість
    -0.07
     sotto
    -0.06
    ريكية
    -0.06
     Welfare
    -0.06
    umo
    -0.06
    .blob
    -0.06
     giorni
    -0.06
     desperation
    -0.06
    双
    -0.06
     PRO
    -0.06
    POSITIVE LOGITS
    /terms
    0.07
     conditioning
    0.07
    ằm
    0.06
    _CRITICAL
    0.06
    setAttribute
    0.06
    .","
    0.06
    clock
    0.06
    ถาน
    0.06
    hex
    0.06
    ="+
    0.06
    Act Density 0.002%

    No Known Activations