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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging actions or suggestions

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

    suggesting tries or guesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.46
    expandindo
    -0.42
    Autowired
    -0.39
    pageY
    -0.38
     outstanding
    -0.34
     constrained
    -0.34
    BitmapFactory
    -0.32
     block
    -0.32
     lunch
    -0.31
     poll
    -0.31
    POSITIVE LOGITS
     autorytatywna
    0.71
    rungsseite
    0.62
    VYMaps
    0.61
    AppMethodBeat
    0.55
     kasarigan
    0.55
    espé
    0.54
    posedge
    0.54
    Personendaten
    0.53
     EconPapers
    0.53
     phoneNumber
    0.50
    Act Density 0.001%

    No Known Activations