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

    Neuronpedia

    INDEX
    Explanations

    words that indicate a change or modification has taken place

    oai_token-act-pair · gemini-2.0-flash

    improved or reduced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.81
    ंदीखरीदारी
    -0.67
    DataAnnotations
    -0.63
    hyrchwyd
    -0.60
    ⓧ
    -0.60
     SafeMath
    -0.59
     GoogleFonts
    -0.59
     umane
    -0.58
     akka
    -0.58
    among
    -0.57
    POSITIVE LOGITS
     super
    0.53
    .*")]
    0.52
    __":
    0.52
    jspx
    0.48
    Personensuche
    0.47
     فريبيس
    0.46
    principalTable
    0.46
    slant
    0.45
     {?>
    0.45
    PCT
    0.44
    Act Density 2.328%

    No Known Activations