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

    Neuronpedia

    INDEX
    Explanations

    listing items or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plana
    0.47
    SNS
    0.44
     اجتماع
    0.43
     alcuni
    0.43
     einigen
    0.43
     inten
    0.43
     こんな
    0.42
     några
    0.42
     plans
    0.42
    ोट
    0.41
    POSITIVE LOGITS
    serviceTime
    0.46
    üedad
    0.41
     physiologically
    0.40
    smithy
    0.40
    srv
    0.39
    ्यता
    0.39
    efficacy
    0.39
    serverResponse
    0.39
    ühle
    0.38
    িনায়ক
    0.38
    Act Density 0.017%

    No Known Activations