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

    Neuronpedia

    INDEX
    Explanations

    derivatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (return
    -0.06
    OKIE
    -0.06
     mommy
    -0.06
     hospitalized
    -0.06
    키
    -0.06
     пласти
    -0.06
    退
    -0.06
    ivist
    -0.06
    -II
    -0.06
    ?page
    -0.06
    POSITIVE LOGITS
     nevy
    0.07
     UT
    0.06
    mer
    0.06
    .addRow
    0.06
    .EXTRA
    0.06
    Pet
    0.06
     perpetrator
    0.06
    ,content
    0.06
    ength
    0.06
    MER
    0.06
    Act Density 0.001%

    No Known Activations