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

    Neuronpedia

    INDEX
    Explanations

    common phrases and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stens
    0.44
    tac
    0.41
    libc
    0.39
    îte
    0.39
    ITURE
    0.39
    azolid
    0.39
    emony
    0.38
    tu
    0.38
    late
    0.38
    ups
    0.38
    POSITIVE LOGITS
     nextline
    0.44
     investments
    0.42
     newcom
    0.40
     Contribution
    0.39
     Glastonbury
    0.39
     insecurity
    0.39
     പെ
    0.39
     windfall
    0.39
     gloss
    0.38
     pril
    0.38
    Act Density 0.000%

    No Known Activations