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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DOMAIN
    -0.07
    809
    -0.07
    WARDS
    -0.07
     upright
    -0.06
     befind
    -0.06
     cycle
    -0.06
    婆
    -0.06
     inning
    -0.06
    ())))
    -0.06
    _original
    -0.06
    POSITIVE LOGITS
     truy
    0.07
    Cho
    0.07
     Identified
    0.07
    emmel
    0.06
     eclips
    0.06
    हम
    0.06
     Analog
    0.06
     or
    0.06
     accelerated
    0.06
     amel
    0.06
    Act Density 0.007%

    No Known Activations