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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "distribution" and related contexts

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

    Text after specific punctuation or code sequences

    np_acts-logits-general · gemini-2.0-flash

    code and configuration details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.52
     “
    -0.52
     "
    -0.48
    ↵↵
    -0.47
     indeed
    -0.46
    eriksaan
    -0.45
     treści
    -0.44
     Roper
    -0.44
    "]="
    -0.43
     
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.89
    ftagPool
    0.80
    tagext
    0.79
    󠁣
    0.79
    Personendaten
    0.76
     cherchés
    0.74
    onAttach
    0.74
    новништво
    0.73
    tvguidetime
    0.72
     createSlice
    0.71
    Act Density 0.085%

    No Known Activations