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

    Neuronpedia

    INDEX
    Explanations

    XML or HTML-like structures and markup

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

    match score and circuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getState
    -0.35
    (!__
    -0.35
     isFirst
    -0.35
    Annexes
    -0.34
    Vtbl
    -0.33
     newUser
    -0.33
    Collective
    -0.33
    Plaintiff
    -0.33
     getPlayer
    -0.32
     gesso
    -0.32
    POSITIVE LOGITS
     match
    1.41
    match
    1.37
     Match
    1.37
     matching
    1.37
     matches
    1.32
    matching
    1.29
    Match
    1.27
     MATCH
    1.26
     Matching
    1.25
    MATCH
    1.23
    Act Density 0.074%

    No Known Activations