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

    Neuronpedia

    INDEX
    Explanations

    references to annual summaries or reviews of past events

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

    "progress"

    np_acts-logits-general · gemini-2.0-flash

    progress and achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.37
    once
    -0.35
    ilah
    -0.34
     Initially
    -0.34
    議院
    -0.33
     Again
    -0.33
    skri
    -0.32
    o
    -0.32
     sarung
    -0.32
    tip
    -0.31
    POSITIVE LOGITS
     progress
    0.57
     للمعارف
    0.56
     achievements
    0.54
     performance
    0.54
    ReusableCell
    0.54
     successes
    0.50
     progresso
    0.49
     arvio
    0.49
     evaluation
    0.49
    DockStyle
    0.49
    Act Density 0.285%

    No Known Activations