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

    Neuronpedia

    INDEX
    Explanations

    repentance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     announcement
    -0.07
    _stderr
    -0.06
     Laden
    -0.06
    ignored
    -0.06
     Brief
    -0.06
     announcements
    -0.06
    оп
    -0.06
     ride
    -0.06
     Winners
    -0.06
     FAQ
    -0.06
    POSITIVE LOGITS
    께서
    0.08
    IGHT
    0.07
    astle
    0.07
     earthqu
    0.07
    oge
    0.06
    MethodImpl
    0.06
     cond
    0.06
     poignant
    0.06
     tears
    0.06
    ㅎ
    0.06
    Act Density 0.008%

    No Known Activations