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
    abant
    -0.07
    яб
    -0.07
    uyen
    -0.07
     νε
    -0.06
     seaborn
    -0.06
     sdf
    -0.06
    abwe
    -0.06
    adows
    -0.06
    icrobial
    -0.06
     narrow
    -0.06
    POSITIVE LOGITS
     Kid
    0.07
    처럼
    0.07
     Typ
    0.06
    قد
    0.06
     BadRequest
    0.06
    estruct
    0.06
     gripping
    0.06
     BX
    0.06
    ế
    0.06
    okit
    0.06
    Act Density 0.001%

    No Known Activations