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

    Neuronpedia

    INDEX
    Explanations

    disclaimer statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibusdam
    0.45
     Silence
    0.40
     Salute
    0.40
    OrFail
    0.39
     específicamente
    0.38
     silence
    0.38
     potencialmente
    0.38
     may
    0.37
     DO
    0.37
     my
    0.37
    POSITIVE LOGITS
    Note
    0.47
    Disclaimer
    0.46
    None
    0.45
    你是
    0.43
    他是
    0.43
    她是
    0.42
    Settings
    0.42
     আলাপ
    0.41
    ន
    0.40
    Fix
    0.40
    Act Density 0.001%

    No Known Activations