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

    Neuronpedia

    INDEX
    Explanations

    instances where the code structure is defined or referenced

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

    code snippets and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.69
    rungsseite
    -0.62
     zuſammen
    -0.59
    évaluateur
    -0.59
     Autorizaciones
    -0.58
     EconPapers
    -0.56
     esternos
    -0.56
    
    -0.55
     müſſen
    -0.55
     ſich
    -0.54
    POSITIVE LOGITS
    verifyException
    0.36
    GenerationType
    0.34
     mármol
    0.33
    endaft
    0.32
     silicona
    0.31
     embarc
    0.31
     películas
    0.29
     déclarations
    0.29
     tarde
    0.29
     retourner
    0.28
    Act Density 0.126%

    No Known Activations