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

    Neuronpedia

    INDEX
    Explanations

    terms related to installation, publication, analysis, and review processes

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

    decisions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſchen
    -0.54
     Photocase
    -0.53
    ロウィン
    -0.51
    MemoryWarning
    -0.50
    enterOuterAlt
    -0.50
    LookAnd
    -0.50
     bureauc
    -0.49
    ஋
    -0.48
     monde
    -0.48
    earcher
    -0.48
    POSITIVE LOGITS
    Билгалдахарш
    0.39
    __':
    0.37
    //
    0.35
    Hochspringen
    0.31
     invokingState
    0.30
    ngths
    0.30
     Speisen
    0.30
     تضيفلها
    0.29
     asleep
    0.29
    ⎥
    0.29
    Act Density 0.162%

    No Known Activations