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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate options or choices

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

    either/or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cipline
    -0.46
     prune
    -0.45
    getWriter
    -0.45
    frastructure
    -0.45
     Prudential
    -0.44
    parsedMessage
    -0.43
     Infórmanos
    -0.42
     Anon
    -0.41
     PUC
    -0.41
     UF
    -0.41
    POSITIVE LOGITS
     gyhoeddwyd
    0.45
    IntoConstraints
    0.44
    posedge
    0.40
     SwitchCompat
    0.40
    Xna
    0.40
    queryInterface
    0.39
     depending
    0.38
    ngdoc
    0.38
    fortawesome
    0.38
     Königin
    0.38
    Act Density 0.034%

    No Known Activations