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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

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

    top or first in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.46
     "..\..\..\
    -0.41
     kaarangay
    -0.40
    تقاوى
    -0.39
    pans
    -0.38
     AssemblyCulture
    -0.38
    ایج
    -0.37
    irited
    -0.36
    chita
    -0.36
     puffs
    -0.35
    POSITIVE LOGITS
    󠁣
    0.49
     للاسماء
    0.49
     recommandée
    0.49
    DockStyle
    0.46
     priority
    0.45
    FunctionFlags
    0.45
    Rohy
    0.43
     highest
    0.43
     prioridad
    0.42
     MainAxisSize
    0.42
    Act Density 0.077%

    No Known Activations