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

    Neuronpedia

    INDEX
    Explanations

    regarding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.76
    endphp
    -0.75
     الرياضيه
    -0.75
    脚注の使い方
    -0.74
    原始内容存档于
    -0.70
    ArrowToggle
    -0.68
    dibles
    -0.68
    ])):
    -0.68
    CodeAttribute
    -0.68
    <bos>
    -0.67
    POSITIVE LOGITS
    .
    0.60
    ism
    0.55
     well
    0.52
     a
    0.51
     long
    0.51
     playing
    0.50
     talking
    0.50
     paying
    0.50
    :
    0.50
     very
    0.49
    Act Density 0.150%

    No Known Activations