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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikh
    -0.07
    ########################################################
    -0.06
     روستا
    -0.06
    比
    -0.06
    gg
    -0.06
     temple
    -0.06
     '${
    -0.06
     ngh
    -0.06
     registered
    -0.06
    -transparent
    -0.06
    POSITIVE LOGITS
     Dread
    0.06
    â
    0.06
     satisf
    0.06
     ZX
    0.06
    ?",
    0.06
    declare
    0.06
     stead
    0.06
     stumble
    0.06
     прис
    0.06
    poň
    0.06
    Act Density 0.147%

    No Known Activations