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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minion
    -0.06
     relocated
    -0.06
     cellul
    -0.06
    lington
    -0.06
    師
    -0.06
    ↵
↵
    -0.06
    leshoot
    -0.06
     wand
    -0.06
    hesion
    -0.06
     readdir
    -0.06
    POSITIVE LOGITS
    писание
    0.07
     Sports
    0.07
    ụp
    0.07
    financial
    0.06
    anja
    0.06
     Guil
    0.06
     ardından
    0.06
     پایان
    0.06
     ServletException
    0.06
    위를
    0.06
    Act Density 0.035%

    No Known Activations