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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pj
    -0.06
     Circuit
    -0.06
    .priority
    -0.06
    367
    -0.06
     Guardian
    -0.06
    >t
    -0.06
    facet
    -0.05
     dept
    -0.05
     Nikon
    -0.05
     Grid
    -0.05
    POSITIVE LOGITS
     Video
    0.07
    очные
    0.07
    _votes
    0.07
    시는
    0.07
     psz
    0.07
    Validators
    0.07
    ونه
    0.07
    emek
    0.07
    Type
    0.07
    ONSE
    0.06
    Act Density 0.001%

    No Known Activations