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

    Neuronpedia

    INDEX
    Explanations

    ia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (egt
    -0.06
     Cup
    -0.06
    908
    -0.06
     Někter
    -0.06
     Patreon
    -0.06
    苦
    -0.06
    .RELATED
    -0.06
     Modern
    -0.06
     кус
    -0.06
     Cats
    -0.06
    POSITIVE LOGITS
    ############################
    0.08
     #↵
    0.07
     ba
    0.07
    -il
    0.07
     김
    0.06
     pok
    0.06
     пох
    0.06
    ？↵↵
    0.06
    arch
    0.06
    ights
    0.06
    Act Density 0.001%

    No Known Activations