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

    Neuronpedia

    INDEX
    Explanations

    brief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -actions
    -0.07
    ERA
    -0.07
    era
    -0.07
    імі
    -0.06
     propTypes
    -0.06
     yani
    -0.06
     kdy
    -0.06
     nothing
    -0.06
     ground
    -0.06
     eaten
    -0.06
    POSITIVE LOGITS
     strav
    0.07
    _marshall
    0.06
    .beginPath
    0.06
    chrift
    0.06
     tomb
    0.06
    (UnmanagedType
    0.06
    acob
    0.06
     trib
    0.06
    /div
    0.06
    储
    0.06
    Act Density 0.005%

    No Known Activations