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

    Neuronpedia

    INDEX
    Explanations

    Ridges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AAAA
    -0.07
    Metadata
    -0.07
     satın
    -0.06
    "indices
    -0.06
    那里
    -0.06
    nickname
    -0.06
    ували
    -0.06
    akeup
    -0.06
    уса
    -0.06
    timer
    -0.06
    POSITIVE LOGITS
    les
    0.07
    .Remote
    0.06
     Humph
    0.06
     ücret
    0.06
     Berger
    0.06
     comprehension
    0.06
    让我
    0.06
     Bearings
    0.06
     behavioral
    0.06
     reproduction
    0.06
    Act Density 0.036%

    No Known Activations