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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the importance and roles of specific elements or factors in various contexts

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

    role in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fotográfico
    -0.43
     maybe
    -0.40
     législ
    -0.39
    \{\\
    -0.35
    Personendaten
    -0.35
    Ẳ
    -0.35
     køb
    -0.34
     tuyo
    -0.33
     PUSTAKA
    -0.33
     några
    -0.32
    POSITIVE LOGITS
    tagHelperRunner
    0.59
    Hozzáférés
    0.54
     ErrIntOverflow
    0.54
    vician
    0.52
    strongly
    0.52
    󠁢
    0.52
     Strongly
    0.52
     brilliantly
    0.52
    Gön
    0.52
    tvguidetime
    0.51
    Act Density 0.065%

    No Known Activations