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

    Neuronpedia

    INDEX
    Explanations

    He + action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Birla
    0.42
     grinding
    0.42
    劃
    0.40
    engan
    0.40
     variations
    0.40
     steig
    0.40
    increasing
    0.39
    بر
    0.39
    bracketing
    0.39
    眅
    0.39
    POSITIVE LOGITS
     güçlü
    0.46
     côtés
    0.44
     następnie
    0.42
    चे
    0.42
     chậm
    0.42
     fortement
    0.42
     confes
    0.42
    에도
    0.41
     스스로
    0.41
     तीसरे
    0.41
    Act Density 0.003%

    No Known Activations