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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accommodate
    -0.07
    .pro
    -0.07
     factor
    -0.07
     complement
    -0.07
     operates
    -0.07
     echt
    -0.07
    .segments
    -0.07
    费
    -0.07
     порядке
    -0.07
     במהלך
    -0.06
    POSITIVE LOGITS
    _Action
    0.08
     �
    0.07
     Webseite
    0.06
    نظ
    0.06
     dracon
    0.06
    ович
    0.06
    .arguments
    0.06
    	Null
    0.06
    -functions
    0.06
     Position
    0.06
    Act Density 0.000%

    No Known Activations