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

    Neuronpedia

    INDEX
    Explanations

    best/greatest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     os
    -0.07
    جي
    -0.07
    Receipt
    -0.06
     the
    -0.06
    onomic
    -0.06
    нии
    -0.06
    اى
    -0.06
     angi
    -0.06
    idd
    -0.06
    -exc
    -0.06
    POSITIVE LOGITS
     très
    0.06
    perhaps
    0.06
    (remove
    0.06
     kitty
    0.06
     sched
    0.06
     Release
    0.06
     Binder
    0.06
     Praze
    0.06
     cialis
    0.06
     TRACE
    0.06
    Act Density 0.096%

    No Known Activations