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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۱۶
    -0.07
     توان
    -0.06
     unsur
    -0.06
    名字
    -0.06
     kelim
    -0.06
     susp
    -0.06
     atmos
    -0.06
    itary
    -0.06
    γρά
    -0.06
     リ
    -0.06
    POSITIVE LOGITS
    syscall
    0.07
    agner
    0.07
    ées
    0.06
    Here
    0.06
     overview
    0.06
    destruct
    0.06
    ávat
    0.06
    polate
    0.06
    わたし
    0.06
     cite
    0.06
    Act Density 0.000%

    No Known Activations