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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "work" and its variations, indicating successful function or operation

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

    works successfully and properly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EIA
    -0.41
     chainsaw
    -0.39
     Ana
    -0.39
     Oc
    -0.38
    unhofer
    -0.38
    Nan
    -0.38
    ⓘ
    -0.38
     Nan
    -0.37
     Derbyshire
    -0.37
    Personensuche
    -0.36
    POSITIVE LOGITS
    GenerationType
    0.54
    CloseOperation
    0.52
    SuccessListener
    0.49
    PreInfinity
    0.49
    EndInit
    0.48
     válida
    0.47
     correcta
    0.47
    zelfde
    0.46
     fonctionnement
    0.46
     gjelder
    0.46
    Act Density 0.050%

    No Known Activations