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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canh
    -0.08
     majors
    -0.07
    onna
    -0.07
    оте
    -0.07
     tren
    -0.07
     tik
    -0.07
    ハ
    -0.07
     hospitalized
    -0.06
     Sleeping
    -0.06
    _Con
    -0.06
    POSITIVE LOGITS
     meanwhile
    0.07
    _TER
    0.06
     flurry
    0.06
     Modifier
    0.06
     chai
    0.06
    lparr
    0.06
     ผ
    0.06
    วย
    0.06
    .contacts
    0.05
     modifier
    0.05
    Act Density 0.042%

    No Known Activations