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

    Neuronpedia

    INDEX
    Explanations

    abysmal, abyssal, AbyssOrange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    overl
    0.42
     lup
    0.41
    logs
    0.39
    member
    0.38
    met
    0.37
     بمع
    0.36
    clean
    0.36
    Pixels
    0.35
    meer
    0.35
    LongNumber
    0.35
    POSITIVE LOGITS
     глуби
    0.42
     party
    0.42
    告诉我
    0.41
     plong
    0.39
    नं
    0.38
    鲛
    0.38
     깊
    0.38
     profundizar
    0.38
    就是一个
    0.38
     τὴν
    0.37
    Act Density 0.004%

    No Known Activations