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

    Neuronpedia

    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esinden
    -0.07
    _imm
    -0.07
     листь
    -0.06
    aniu
    -0.06
     chuyên
    -0.06
    子の
    -0.06
    vc
    -0.06
    inden
    -0.06
    odings
    -0.06
    丈夫
    -0.06
    POSITIVE LOGITS
    ARGER
    0.07
     Hav
    0.07
     Epic
    0.06
     HI
    0.06
     Purdue
    0.06
     "<?
    0.06
    <Article
    0.06
    (Core
    0.06
    >`
    0.06
     Mog
    0.06
    Act Density 0.003%

    No Known Activations