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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of the "Fourth Wall"

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

    author names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.74
     imagui
    -0.69
    principalColumn
    -0.69
     ſeines
    -0.66
    ThroughAttribute
    -0.66
    ᔢ
    -0.65
     $_-
    -0.65
    -0.65
     BorderRadius
    -0.65
    iſche
    -0.64
    POSITIVE LOGITS
     hjemme
    0.26
     hyvä
    0.26
     Texte
    0.25
     Audience
    0.24
     plezier
    0.24
    ()],
    0.24
     plankton
    0.23
     keterangan
    0.23
     audience
    0.23
     notas
    0.23
    Act Density 0.060%

    No Known Activations