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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intent

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

    for phrases and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pungkas
    -0.40
    Chham
    -0.39
    ifiquement
    -0.38
     niebla
    -0.37
    ovací
    -0.34
    getOr
    -0.34
    ními
    -0.32
    Fordítás
    -0.32
     financiero
    -0.31
     Hoffnung
    -0.31
    POSITIVE LOGITS
    contentLoaded
    0.62
     متعلقه
    0.58
     utafitiHapana
    0.57
     having
    0.56
     <>",
    0.55
    having
    0.54
     betterment
    0.53
    better
    0.53
     better
    0.52
    resaid
    0.52
    Act Density 0.051%

    No Known Activations