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

    Neuronpedia

    INDEX
    Explanations

    sentient, sent, sentiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    1.37
    (
    1.16
    CS
    1.13
    ag
    1.13
    k
    1.12
    ü
    1.12
    ை
    1.09
    ut
    1.09
    डी
    1.09
    t
    1.09
    POSITIVE LOGITS
     bhave
    1.02
     punctato
    0.97
    Sent
    0.93
     religieux
    0.92
     он
    0.90
    。
    0.88
     hormati
    0.88
    sent
    0.86
    ।
    0.83
     potencia
    0.83
    Act Density 0.005%

    No Known Activations