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

    Neuronpedia

    INDEX
    Explanations

    humanity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تانيه
    -1.45
    TagMode
    -1.30
     beginnetje
    -1.22
     '\\;'
    -1.22
     AssemblyCulture
    -1.20
     فريبيس
    -1.20
     مرئيه
    -1.18
     صوتيه
    -1.16
    +#+#
    -1.15
     feroit
    -1.15
    POSITIVE LOGITS
    ing
    0.81
    ,
    0.70
    s
    0.69
    -
    0.69
     
    0.68
    ↵
    0.67
     '
    0.67
    .
    0.65
    ally
    0.62
    ↵↵
    0.61
    Act Density 1.499%

    No Known Activations