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

    Neuronpedia

    INDEX
    Explanations

    code, config files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROUP
    -0.07
     μικ
    -0.07
    ову
    -0.07
     Copa
    -0.06
    bracht
    -0.06
     Barbar
    -0.06
    SX
    -0.06
     RT
    -0.06
     pady
    -0.06
     Christie
    -0.06
    POSITIVE LOGITS
    aus
    0.07
     legit
    0.07
    .selected
    0.06
    .linear
    0.06
     description
    0.06
    okin
    0.06
    image
    0.06
    Ben
    0.06
     popover
    0.06
    0.06
    Act Density 0.282%

    No Known Activations