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

    Neuronpedia

    INDEX
    Explanations

    ation/ration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "<
    -0.07
     circular
    -0.07
     Clippers
    -0.06
     permanently
    -0.06
    389
    -0.06
    .execute
    -0.06
    刷
    -0.06
     Orn
    -0.06
    444
    -0.06
    733
    -0.06
    POSITIVE LOGITS
     ration
    0.23
    ationale
    0.10
     rationale
    0.09
    ration
    0.08
    osomal
    0.07
     demean
    0.07
    меть
    0.07
    Animating
    0.07
     raison
    0.07
    .chart
    0.07
    Act Density 0.005%

    No Known Activations