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

    Neuronpedia

    INDEX
    Explanations

    nvidia-smi, rail, format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itochond
    0.42
     ტი
    0.40
    ytail
    0.39
    )”
    0.39
    মোহ
    0.39
    itoneal
    0.38
    _"+
    0.38
    --’
    0.38
    ospheric
    0.38
    ppermint
    0.37
    POSITIVE LOGITS
    ‐
    0.58
    *-
    0.56
    based
    0.54
    первых
    0.54
    &-
    0.51
    dessous
    0.48
    *,
    0.47
    induced
    0.45
    related
    0.44
    delà
    0.41
    Act Density 0.057%

    No Known Activations