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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to enumeration or listing items

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

    Einheldenblen, Einherjar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.60
    ValueStyle
    -0.57
     zijne
    -0.54
     zoude
    -0.53
     parachoque
    -0.52
     dezelve
    -0.52
     semelh
    -0.51
     waard
    -0.50
     dianteira
    -0.50
     toalha
    -0.49
    POSITIVE LOGITS
     into
    0.85
     Ein
    0.84
     einge
    0.79
     einzu
    0.78
     entry
    0.77
    Ein
    0.74
    入
    0.73
     Eins
    0.72
    Into
    0.71
     Into
    0.70
    Act Density 0.006%

    No Known Activations