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

    Neuronpedia

    INDEX
    Explanations

    50

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     absolute
    -0.09
     absolut
    -0.08
    ké
    -0.08
     प्रयोग
    -0.08
     kilom
    -0.08
     coolant
    -0.08
    тот
    -0.08
     kettle
    -0.08
    …).
    -0.08
    ittle
    -0.08
    POSITIVE LOGITS
     score
    0.13
    -score
    0.13
    score
    0.12
    	score
    0.12
    scores
    0.12
     scores
    0.12
    Scores
    0.11
    .score
    0.11
    Score
    0.11
     Score
    0.10
    Act Density 0.024%

    No Known Activations