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

    Neuronpedia

    INDEX
    Explanations

    pronouns at start of clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.93
    م
    0.88
    ט
    0.84
    ر
    0.76
    ום
    0.73
    ف
    0.73
    Μ
    0.73
    ه
    0.72
    ിക്ക
    0.71
    ਸ
    0.68
    POSITIVE LOGITS
    dec
    1.00
    ni
    0.95
    devices
    0.92
    d
    0.92
    daten
    0.91
    ca
    0.89
    g
    0.89
    data
    0.88
    da
    0.88
    den
    0.86
    Act Density 0.099%

    No Known Activations