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

    Neuronpedia

    INDEX
    Explanations

    by/from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Р
    -0.07
     보호
    -0.06
     improvement
    -0.06
    iz
    -0.06
     denied
    -0.06
     maintained
    -0.06
     elem
    -0.06
    _near
    -0.06
     specifier
    -0.06
     tricks
    -0.06
    POSITIVE LOGITS
    ，”
    0.07
    YNAMIC
    0.06
    itunes
    0.06
    .k
    0.06
    ylan
    0.06
    .XtraEditors
    0.06
     Poster
    0.06
     isArray
    0.06
     fictional
    0.06
     än
    0.06
    Act Density 0.024%

    No Known Activations