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

    Neuronpedia

    INDEX
    Explanations

    Published posthumously

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .eclipse
    -0.07
    �
    -0.07
     wi
    -0.07
    .plot
    -0.07
    bfd
    -0.07
     MED
    -0.07
    spect
    -0.07
     sm
    -0.07
    pthread
    -0.06
    pects
    -0.06
    POSITIVE LOGITS
    ▓
    0.08
     scalp
    0.08
     kans
    0.07
    玓
    0.07
     Erdoğan
    0.07
     scoff
    0.07
     Duel
    0.07
    רגש
    0.06
    Cast
    0.06
     заказ
    0.06
    Act Density 0.072%

    No Known Activations