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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    019
    -0.07
    ريكية
    -0.07
     color
    -0.07
     diagnostics
    -0.06
    syscall
    -0.06
    中央
    -0.06
    _TI
    -0.06
     scan
    -0.06
    syn
    -0.06
     موارد
    -0.06
    POSITIVE LOGITS
    :white
    0.06
     Roc
    0.06
    ).
↵
    0.06
     strategies
    0.06
    idel
    0.06
    тим
    0.06
    istinguish
    0.05
    leting
    0.05
    stadt
    0.05
     altering
    0.05
    Act Density 0.091%

    No Known Activations