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

    Neuronpedia

    INDEX
    Explanations

    []{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )))↵↵↵
    -0.07
     orc
    -0.07
     ประก
    -0.06
    鐵
    -0.06
    World
    -0.06
     sacrifices
    -0.06
     Stud
    -0.06
     Tor
    -0.06
     goddess
    -0.06
     devast
    -0.06
    POSITIVE LOGITS
     selectively
    0.07
    .Abstract
    0.06
    mpz
    0.06
     fingertips
    0.06
    _ctrl
    0.06
    管
    0.06
     synthesized
    0.06
     Nano
    0.06
     unrestricted
    0.06
    Appointment
    0.06
    Act Density 0.000%

    No Known Activations