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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dinners
    -0.07
    -set
    -0.07
     providers
    -0.07
    _location
    -0.07
    ervations
    -0.06
    αιο
    -0.06
     dies
    -0.06
    (provider
    -0.06
     \\
    -0.06
    (board
    -0.06
    POSITIVE LOGITS
     из
    0.08
    _green
    0.06
     forefront
    0.06
    ovými
    0.06
    ักก
    0.06
     downward
    0.06
     Flake
    0.06
    ervo
    0.05
    tvrt
    0.05
    .XtraPrinting
    0.05
    Act Density 0.010%

    No Known Activations