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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     توق
    -0.07
     noises
    -0.06
    utorial
    -0.06
     Spare
    -0.06
    !");↵↵
    -0.06
     Savior
    -0.06
    .GetCurrentMethod
    -0.06
     پاسخ
    -0.06
     Siemens
    -0.06
     UserRole
    -0.06
    POSITIVE LOGITS
    ским
    0.07
    dropdown
    0.07
     那
    0.06
    ському
    0.06
    skou
    0.06
     hm
    0.06
     indem
    0.06
    ковий
    0.06
     demok
    0.06
    does
    0.06
    Act Density 0.007%

    No Known Activations