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

    Neuronpedia

    INDEX
    Explanations

    www. or website addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ena
    0.46
    lij
    0.42
    jada
    0.42
     cui
    0.40
    klu
    0.39
     buurt
    0.38
    uminação
    0.38
    ene
    0.38
    ham
    0.38
    gação
    0.37
    POSITIVE LOGITS
     hugely
    0.39
     Folklore
    0.39
     wildly
    0.39
     happily
    0.38
    ༻
    0.38
     triumphs
    0.38
     glories
    0.38
     sumptuous
    0.37
     achievable
    0.37
     వి
    0.36
    Act Density 0.001%

    No Known Activations