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

    Neuronpedia

    INDEX
    Explanations

    large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intah
    0.38
    hom
    0.36
     acknowledging
    0.35
    gea
    0.35
    eria
    0.35
    Cleveland
    0.35
     Sonnen
    0.35
    StateType
    0.35
     Acts
    0.34
    venidos
    0.34
    POSITIVE LOGITS
     cancelButton
    0.44
     опас
    0.43
     hiểm
    0.42
     SHOW
    0.41
     шоу
    0.41
     reversal
    0.40
     göster
    0.40
     juda
    0.40
     cardNumber
    0.40
     Dangerous
    0.39
    Act Density 0.023%

    No Known Activations