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

    Neuronpedia

    INDEX
    Explanations

    spam and infected attachments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    putation
    0.40
     सोते
    0.40
     регуляр
    0.39
    peror
    0.39
    temporal
    0.38
    hydrogen
    0.38
     탱
    0.38
    劣
    0.38
     validar
    0.37
     регионе
    0.37
    POSITIVE LOGITS
     attachments
    2.00
     attachment
    1.90
    附件
    1.81
     attached
    1.77
    Attachments
    1.69
    attachments
    1.67
     Attach
    1.60
     Attached
    1.60
    attachment
    1.59
     Attachment
    1.59
    Act Density 0.013%

    No Known Activations