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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'gc
    -0.09
    emey
    -0.07
    ANJI
    -0.07
    enek
    -0.06
    á»ijc
    -0.06
    iore
    -0.06
    LARI
    -0.06
     mädchen
    -0.06
    ÄĽle
    -0.06
    daki
    -0.06
    POSITIVE LOGITS
     either
    0.07
     both
    0.06
    ither
    0.06
    itter
    0.06
    ãĥ¼ãĥ
    0.06
    ä¸ģ缮
    0.06
     direct
    0.06
    occ
    0.05
     eg
    0.05
     imperfect
    0.05
    Act Density 0.073%

    No Known Activations