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
    �
    -0.07
     rooft
    -0.07
     Square
    -0.06
     towards
    -0.06
    incorrect
    -0.06
     toward
    -0.06
    یم
    -0.06
    (val
    -0.06
     SQUARE
    -0.06
    .JSON
    -0.06
    POSITIVE LOGITS
    ября
    0.07
     частина
    0.07
    sez
    0.06
    bedtls
    0.06
     nuovo
    0.06
    nilai
    0.06
     fascinated
    0.06
     •
    0.06
     Introduced
    0.06
    }//
    0.06
    Act Density 0.075%

    No Known Activations