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

    Neuronpedia

    INDEX
    Explanations

    Substitute, Needs, strategic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.64
    race
    0.61
    anvil
    0.52
     смя
    0.49
    hled
    0.48
    qal
    0.48
    motif
    0.48
    ppe
    0.47
    ell
    0.46
     prize
    0.46
    POSITIVE LOGITS
    وں
    0.52
    연
    0.45
    영화
    0.45
    ہی
    0.45
    は
    0.44
    은
    0.44
    ون
    0.43
     او
    0.43
    는
    0.43
    是很
    0.43
    Act Density 0.000%

    No Known Activations