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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RegexOptions
    -0.07
    니아
    -0.06
     dove
    -0.06
     vite
    -0.06
    isecond
    -0.06
    iban
    -0.06
    ’.
    -0.06
     sniff
    -0.06
    -Oct
    -0.06
     disple
    -0.06
    POSITIVE LOGITS
     Springs
    0.07
     inmates
    0.06
     blanks
    0.06
    3
    0.06
     Missing
    0.06
     Dental
    0.06
    ANCE
    0.06
    ,default
    0.06
    nda
    0.06
    선
    0.06
    Act Density 0.004%

    No Known Activations