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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of adjustable GUI or CSS style properties (e.g. background color, width, font size).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     choses
    -0.07
    ardon
    -0.07
    etin
    -0.06
    opor
    -0.06
    orpion
    -0.06
     Nah
    -0.06
    坚
    -0.06
     laminate
    -0.06
    	or
    -0.06
    CCCC
    -0.06
    POSITIVE LOGITS
     tiếp
    0.07
     DIY
    0.07
    ъек
    0.07
    ~↵↵
    0.06
    тю
    0.06
     місцев
    0.06
    !!!↵↵
    0.06
    aciones
    0.06
    �
    0.06
    ibil
    0.06
    Act Density 0.137%

    No Known Activations