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

    Neuronpedia

    INDEX
    Explanations

    chappal and roti

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     narration
    0.43
     зав
    0.40
     narrated
    0.40
     narr
    0.39
     zar
    0.38
    ̣t
    0.38
    trimethyl
    0.36
    erial
    0.35
     Narr
    0.35
     периода
    0.34
    POSITIVE LOGITS
     chap
    0.66
     rot
    0.62
     Chap
    0.54
     Rot
    0.52
    rot
    0.51
     ч
    0.49
     rota
    0.49
     rotational
    0.48
    Rot
    0.47
    Chap
    0.47
    Act Density 0.001%

    No Known Activations