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

    Neuronpedia

    INDEX
    Explanations

    comparative structures or phrases indicating similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    as ... as comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CNP
    -0.42
    姊
    -0.39
    although
    -0.39
    تج
    -0.38
    cloudflare
    -0.37
    SNAP
    -0.36
    ideration
    -0.36
    مؤ
    -0.35
    FDP
    -0.35
     dene
    -0.35
    POSITIVE LOGITS
    OGND
    0.59
    Източници
    0.54
     esternos
    0.53
    ISupport
    0.52
     zijne
    0.52
     Ephraim
    0.52
     Shakspeare
    0.52
    ConstraintMaker
    0.52
    htä
    0.51
    Parcelize
    0.51
    Act Density 0.153%

    No Known Activations