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

    Neuronpedia

    INDEX
    Explanations

    terms related to machinery or technological processes

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

    Technical or procedural descriptions

    np_acts-logits-general · gemini-2.0-flash

    specify the behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     early
    -0.56
    WarningLevel
    -0.56
    early
    -0.53
     شو
    -0.51
     EARLY
    -0.48
     recently
    -0.47
    Early
    -0.46
    gway
    -0.46
    nost
    -0.45
     الجميع
    -0.45
    POSITIVE LOGITS
     humains
    0.61
    AnimationsModule
    0.59
    makeText
    0.57
    ethene
    0.57
    AnimationFrame
    0.57
    achella
    0.56
     CRUD
    0.56
     الرياضيه
    0.56
     abstrait
    0.56
    uvw
    0.55
    Act Density 0.555%

    No Known Activations