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

    Neuronpedia

    INDEX
    Explanations

    places and their features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acara
    0.54
    bcrypt
    0.50
    echolog
    0.50
    i
    0.49
    bao
    0.47
    eské
    0.47
    pe
    0.47
     જેના
    0.46
    pem
    0.45
    mc
    0.45
    POSITIVE LOGITS
    ิท
    0.48
    ваемых
    0.44
    ет
    0.40
    োগ
    0.39
    आईपी
    0.39
    ปล
    0.39
    ฝ
    0.39
     deb
    0.38
     variously
    0.38
    \
    0.38
    Act Density 0.012%

    No Known Activations