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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    binding
    -0.07
    	DBG
    -0.07
    ="
    -0.06
     Mundo
    -0.06
    cmd
    -0.06
    (Build
    -0.06
    SETTING
    -0.06
     ergonomic
    -0.06
    ushed
    -0.06
     LocalDateTime
    -0.06
    POSITIVE LOGITS
     council
    0.06
     dítě
    0.06
    'é
    0.06
     bumper
    0.06
    旅行
    0.06
    發展
    0.06
     sno
    0.06
     října
    0.06
    ’é
    0.06
     fuller
    0.06
    Act Density 0.002%

    No Known Activations