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

    Neuronpedia

    INDEX
    Explanations

    Advice and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الش
    -0.08
    lead
    -0.08
    rollback
    -0.07
    762
    -0.07
     acr
    -0.07
    ำน
    -0.07
     SYMBOL
    -0.07
    .ALL
    -0.07
     mont
    -0.07
     המת
    -0.07
    POSITIVE LOGITS
     préciser
    0.10
     discussing
    0.09
     mention
    0.09
     conclusion
    0.08
     discuss
    0.08
    Corona
    0.08
     analogy
    0.08
     takeaway
    0.08
     clarification
    0.08
    この記事
    0.08
    Act Density 0.553%

    No Known Activations