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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax or code structure

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mauva
    -0.51
     avoient
    -0.48
     dévelo
    -0.47
    pensione
    -0.47
     neceſſ
    -0.44
    cardinal
    -0.43
     paſſ
    -0.43
    Beneficios
    -0.43
    اقرأ
    -0.43
     kapture
    -0.42
    POSITIVE LOGITS
     []:
    6.44
    /**
    1.06
    
    1.03
     snippetHide
    0.98
    /*:
    0.89
     <<<<<<<<<<<<<<
    0.88
    
    0.86
    ynb
    0.86
    adaptiveStyles
    0.85
     defaultstate
    0.85
    Act Density 0.000%

    No Known Activations