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

    Neuronpedia

    INDEX
    Explanations

    Code/formatting snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dimension
    -0.07
    	cnt
    -0.06
     Bow
    -0.06
     room
    -0.06
     {}
↵
↵
    -0.06
    -negative
    -0.06
    -angular
    -0.06
    ари
    -0.06
     paso
    -0.06
    जह
    -0.06
    POSITIVE LOGITS
    Lead
    0.06
    odian
    0.06
    琳
    0.06
     nek
    0.06
    ?!
    0.06
     itir
    0.06
     hakk
    0.06
     ông
    0.06
     birisi
    0.06
    兰
    0.06
    Act Density 0.218%

    No Known Activations