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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cpu
    -0.07
     Faculty
    -0.07
    게임
    -0.06
    [vertex
    -0.06
    ]"
    -0.06
    can
    -0.06
    ،
    -0.06
    588
    -0.06
    operations
    -0.06
    (et
    -0.06
    POSITIVE LOGITS
    _ISO
    0.07
     extravagant
    0.07
    Tap
    0.06
    RB
    0.06
     Bail
    0.06
    underscore
    0.06
    izzly
    0.06
     mua
    0.06
     Moto
    0.06
     Keys
    0.06
    Act Density 0.003%

    No Known Activations