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

    Neuronpedia

    INDEX
    Explanations

    strings related to user favorites or preferences in a digital context

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    reverse or undo action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ophilic
    -0.53
     doInBackground
    -0.49
    ạo
    -0.47
    ILED
    -0.46
    ophiles
    -0.46
     ويكي
    -0.46
    orei
    -0.46
    osex
    -0.45
     batte
    -0.45
    riba
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.92
     reverting
    0.91
     reverse
    0.91
     undoing
    0.91
     revert
    0.89
     reverted
    0.87
     reversing
    0.87
    reverse
    0.84
     reverses
    0.83
    ScopeManager
    0.83
    Act Density 0.267%

    No Known Activations