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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٣
    -0.08
    _numpy
    -0.07
    י
    -0.07
     OT
    -0.07
    oload
    -0.07
    ğen
    -0.07
    061
    -0.07
     :",
    -0.06
    Joseph
    -0.06
     Muss
    -0.06
    POSITIVE LOGITS
    TA
    0.06
    .vs
    0.06
     footing
    0.06
     Locations
    0.06
     boiler
    0.06
    .r
    0.06
     곳
    0.06
     gro
    0.06
     personnel
    0.06
    izzling
    0.06
    Act Density 0.000%

    No Known Activations