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

    Neuronpedia

    INDEX
    Explanations

    rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     science
    -0.07
     Science
    -0.06
    ToLeft
    -0.06
     Queen
    -0.06
    aceae
    -0.06
     wave
    -0.06
     reconciliation
    -0.06
     SharedPreferences
    -0.06
     weave
    -0.06
    _chain
    -0.06
    POSITIVE LOGITS
     rating
    0.08
     ratings
    0.08
    minent
    0.07
    itung
    0.07
     Rating
    0.07
     дат
    0.07
    र
    0.06
    very
    0.06
    outing
    0.06
    ktor
    0.06
    Act Density 0.009%

    No Known Activations