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

    Neuronpedia

    INDEX
    Explanations

    Dragonflies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     عامة
    -0.07
    led
    -0.07
    ิส
    -0.07
    bus
    -0.07
     ＼↵
    -0.07
                
    -0.06
    车
    -0.06
    imps
    -0.06
    PCS
    -0.06
     інститут
    -0.06
    POSITIVE LOGITS
     прож
    0.07
    arsity
    0.06
     PROC
    0.06
     kurs
    0.06
    otech
    0.06
    <f
    0.06
    ReadWrite
    0.06
     identifies
    0.06
    _CALLBACK
    0.06
    *$
    0.06
    Act Density 0.027%

    No Known Activations