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

    Neuronpedia

    INDEX
    Explanations

    database references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behavioral
    -0.07
    Joy
    -0.06
     swagger
    -0.06
     mamma
    -0.06
    aturdays
    -0.06
    BOOLEAN
    -0.06
     Joy
    -0.06
     Betty
    -0.06
    tz
    -0.06
     centroid
    -0.06
    POSITIVE LOGITS
     ------------------------------------------------
    0.07
    <HTMLInputElement
    0.07
    pired
    0.07
    buquerque
    0.06
     verir
    0.06
    orianCalendar
    0.06
    incip
    0.06
     CrossRef
    0.06
    とな
    0.06
     The
    0.06
    Act Density 0.111%

    No Known Activations