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

    Neuronpedia

    INDEX
    Explanations

    the discussion of methods and the need for new ones.

    oai_token-act-pair · gemini-2.0-flash

    necessity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     createSlice
    -0.53
    RelativeTo
    -0.49
    wapV
    -0.49
     الاطلاع
    -0.47
     relative
    -0.46
    <bos>
    -0.46
    StylePriority
    -0.46
    lwjgl
    -0.45
    AddComponent
    -0.45
    uslar
    -0.45
    POSITIVE LOGITS
     ISNI
    0.75
     Normdatei
    0.57
    --;
    0.57
    (;;)
    0.56
     neutre
    0.56
    IsContent
    0.55
     théorie
    0.54
    あれば
    0.54
    ContentAsync
    0.53
    __);
    0.52
    Act Density 3.552%

    No Known Activations