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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/Characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Innovative
    -0.07
    Ur
    -0.07
     Đức
    -0.07
    oded
    -0.07
     Flood
    -0.06
    SW
    -0.06
     attractions
    -0.06
     Infer
    -0.06
     Invisible
    -0.06
    Notification
    -0.06
    POSITIVE LOGITS
     नए
    0.06
     astro
    0.06
    ='<?
    0.06
    (hist
    0.06
    ,title
    0.06
    ungeons
    0.06
     UAV
    0.06
    ครง
    0.06
     apopt
    0.06
     Trab
    0.06
    Act Density 0.079%

    No Known Activations