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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DESCRIPTOR
    -0.07
    -fat
    -0.06
     needing
    -0.06
     parachute
    -0.06
     holidays
    -0.06
     favors
    -0.06
     пло
    -0.06
     nighttime
    -0.06
    _customize
    -0.06
     Triumph
    -0.06
    POSITIVE LOGITS
    ulnerable
    0.07
    ān
    0.06
     [@
    0.06
    انو
    0.06
     mejor
    0.06
    (print
    0.06
     resultat
    0.06
     stigma
    0.06
    inq
    0.06
    IMENT
    0.06
    Act Density 0.059%

    No Known Activations