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

    Neuronpedia

    INDEX
    Explanations

    words expressing opinion or perspective

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

    Followed by verbs and commas

    np_acts-logits-general · gemini-2.0-flash

    even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.85
    windowFixed
    -0.73
    ביוגרפיה
    -0.66
     '\\;'
    -0.63
     @"";
    -0.63
    MessageTagHelper
    -0.59
    いかに
    -0.56
     numberOfRows
    -0.54
    뷔
    -0.54
    とにかく
    -0.53
    POSITIVE LOGITS
     sogar
    1.16
     even
    1.09
     zelfs
    0.95
     addirittura
    0.94
     persino
    0.90
     אף
    0.88
    even
    0.87
     даже
    0.83
     dokonce
    0.83
     sometimes
    0.82
    Act Density 0.223%

    No Known Activations