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

    Neuronpedia

    INDEX
    Explanations

    roller

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    єте
    -0.08
     склад
    -0.08
     लगत
    -0.07
     arrogant
    -0.07
    stars
    -0.07
     첨부
    -0.06
    �
    -0.06
    gly
    -0.06
     LD
    -0.06
     "%
    -0.06
    POSITIVE LOGITS
    ounds
    0.06
    XMLLoader
    0.06
    struction
    0.06
     Volvo
    0.06
    scanner
    0.06
    OptionsMenu
    0.06
     REC
    0.06
     remains
    0.05
     Trường
    0.05
    urrection
    0.05
    Act Density 0.030%

    No Known Activations