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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references commonly found in coding or legal documents

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

    Follows "wills", "evidence", or "framework"

    np_acts-logits-general · gemini-2.0-flash

    evidence presented, draft picks, what He wills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.93
     Monfieur
    -0.93
    sizeCache
    -0.92
    Vidite
    -0.89
     itſelf
    -0.89
     мәкал
    -0.87
     ―――――
    -0.86
     >=",
    -0.85
    MergeFrom
    -0.85
     Theſe
    -0.84
    POSITIVE LOGITS
    ↵↵
    0.50
    Chham
    0.49
     once
    0.44
    once
    0.43
     tasca
    0.40
     presa
    0.40
    chtigkeit
    0.40
    Once
    0.39
    -
    0.39
     (
    0.38
    Act Density 0.065%

    No Known Activations