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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment towards contributors or mentors

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

    thanks for comments and guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.49
    исленность
    -0.48
     depred
    -0.48
    申し上げます
    -0.48
    stateMutability
    -0.48
     Parity
    -0.46
    shtml
    -0.45
    onews
    -0.45
     pales
    -0.44
     mates
    -0.44
    POSITIVE LOGITS
     guidance
    0.71
     guide
    0.61
     guiding
    0.59
     patiently
    0.55
     patience
    0.55
     guida
    0.52
     guided
    0.51
    guide
    0.50
    guidance
    0.50
     always
    0.48
    Act Density 0.015%

    No Known Activations