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

    Neuronpedia

    INDEX
    Explanations

    mentions of television seasons and episodes

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

    beginnings and phases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.47
     فريبيس
    -0.46
    finish
    -0.42
     finish
    -0.42
     FINISH
    -0.41
    Finish
    -0.41
     drau
    -0.40
     bibl
    -0.39
    -0.38
    ArgsConstructor
    -0.38
    POSITIVE LOGITS
    はじめに
    0.50
    fjspx
    0.49
    Parcelable
    0.47
    開始
    0.46
     begins
    0.45
     beginnt
    0.44
     angekommen
    0.44
     início
    0.43
    始まる
    0.43
    开始
    0.43
    Act Density 0.119%

    No Known Activations