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

    Neuronpedia

    INDEX
    Explanations

    variable assignments and references in programming code

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

    Code assignments and data structures

    np_acts-logits-general · gemini-2.0-flash

    code syntax or structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?")
    -0.68
    ?')
    -0.65
     favourably
    -0.65
    Portail
    -0.65
     barefoot
    -0.64
    Hozzáférés
    -0.63
     öffnungszeiten
    -0.63
    ...?"
    -0.62
    ?
    -0.61
     ){
    -0.59
    POSITIVE LOGITS
     []
    0.92
    =[]
    0.89
     {}
    0.85
    :[]
    0.85
     [];
    0.83
     [],
    0.70
    {}
    0.70
     =[]
    0.69
    =[];
    0.68
    >[]
    0.66
    Act Density 0.117%

    No Known Activations