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

    Neuronpedia

    INDEX
    Explanations

    chart types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     successors
    0.38
    ರಿಕ
    0.37
    predictors
    0.37
     succeeds
    0.36
     پردا
    0.36
     Pandora
    0.35
     வெற்ற
    0.35
    われています
    0.35
     shan
    0.34
     Samir
    0.34
    POSITIVE LOGITS
     טוב
    0.42
     ጥቅም
    0.42
     lehető
    0.42
    amen
    0.41
     галу
    0.41
    icollis
    0.41
     önemlidir
    0.41
     좋
    0.40
    ἐ
    0.40
     Demonstration
    0.39
    Act Density 0.000%

    No Known Activations