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

    Neuronpedia

    INDEX
    Explanations

    terms related to analysis and observation across various contexts

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

    contrasting or comparing two things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.65
    Хьажоргаш
    -0.59
     autorytatywna
    -0.56
     ویکی‌پدی
    -0.55
    Sklici
    -0.54
    цездатний
    -0.54
    oa̍t
    -0.52
    __':
    -0.50
     المعيارى
    -0.50
     {?}
    -0.49
    POSITIVE LOGITS
     sebaliknya
    0.47
     altrett
    0.45
     Dage
    0.42
     bổ
    0.42
     dilan
    0.41
    Middle
    0.40
     Conversely
    0.40
    另一
    0.39
     păr
    0.38
     conversely
    0.38
    Act Density 1.183%

    No Known Activations