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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    债
    -0.07
     aloud
    -0.06
     ELSE
    -0.06
    Los
    -0.06
    ,,,,
    -0.06
    ляться
    -0.06
     hugged
    -0.06
    .BLL
    -0.06
    rací
    -0.06
     vos
    -0.05
    POSITIVE LOGITS
    (Server
    0.08
    /Auth
    0.08
    72
    0.07
     avg
    0.07
    weigh
    0.06
    ्वच
    0.06
    prix
    0.06
     Level
    0.06
    classed
    0.06
    evity
    0.06
    Act Density 0.021%

    No Known Activations