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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oli
    -0.06
     Ост
    -0.06
    	buff
    -0.06
     Howell
    -0.06
    	option
    -0.06
     core
    -0.06
     inward
    -0.06
     Covent
    -0.06
    InlineData
    -0.06
    !--
    -0.06
    POSITIVE LOGITS
     nghi
    0.08
    娜
    0.07
    PRE
    0.06
    ITUDE
    0.06
     aliqu
    0.06
    allas
    0.06
     improvised
    0.06
    波
    0.06
    _ASSIGN
    0.06
    ندية
    0.06
    Act Density 0.035%

    No Known Activations