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

    Neuronpedia

    INDEX
    Explanations

    programming/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Academ
    -0.07
    Kid
    -0.07
     Deg
    -0.07
    ToF
    -0.06
     подход
    -0.06
     Nearby
    -0.06
    -Men
    -0.06
    Slinky
    -0.06
     gem
    -0.06
     scrolls
    -0.06
    POSITIVE LOGITS
     watershed
    0.07
     summit
    0.06
     ORDER
    0.06
     statistical
    0.06
     reconc
    0.06
    (act
    0.06
    (INFO
    0.06
     enrolled
    0.06
    program
    0.06
    sex
    0.06
    Act Density 0.279%

    No Known Activations