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

    Neuronpedia

    INDEX
    Explanations

    after certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihre
    0.50
     ulcerative
    0.46
     правильно
    0.44
    ócz
    0.43
     ue
    0.43
     supplémentaire
    0.42
     volunte
    0.42
     etwa
    0.42
     cucumbers
    0.42
     attivo
    0.42
    POSITIVE LOGITS
     திருவ
    0.44
    晗
    0.42
    alini
    0.40
     Magic
    0.40
    ילות
    0.40
    岡田
    0.40
     Next
    0.38
    影视
    0.38
    elda
    0.38
    បុ
    0.38
    Act Density 0.002%

    No Known Activations