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

    Neuronpedia

    INDEX
    Explanations

    way something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၈
    0.45
     procédés
    0.44
    ْ
    0.43
     dwelling
    0.43
    ٠
    0.42
    Participant
    0.41
    <0xB8>
    0.41
    ють
    0.41
    ٩
    0.41
    rophot
    0.40
    POSITIVE LOGITS
    ic
    0.61
    itan
    0.57
     advise
    0.50
     धारण
    0.50
     अहंकार
    0.48
    wart
    0.48
     อีก
    0.46
    ik
    0.46
    ues
    0.46
     станет
    0.46
    Act Density 0.001%

    No Known Activations