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

    Neuronpedia

    INDEX
    Explanations

    points of view and perspectives in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    biggest problem is overscoping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     then
    -0.56
     dann
    -0.54
     aber
    -0.53
     but
    -0.53
     six
    -0.49
    Then
    -0.48
     infine
    -0.47
     But
    -0.47
     pero
    -0.47
     Dann
    -0.46
    POSITIVE LOGITS
     itſelf
    0.92
     autorytatywna
    0.91
    \{\\
    0.86
     تضيفلها
    0.86
     AssemblyTitle
    0.79
    uxxxx
    0.77
     myſelf
    0.77
     fhew
    0.76
     CURIAM
    0.76
    ьаж
    0.76
    Act Density 0.411%

    No Known Activations