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

    Neuronpedia

    INDEX
    Explanations

    expressions related to mathematical notation and symbols

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

    Mathematical or symbolic notation

    np_acts-logits-general · gemini-2.0-flash

    | as separator or absolute value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nawr
    -0.71
     noDo
    -0.68
    FontStyle
    -0.64
    ::-
    -0.61
     resourceCulture
    -0.59
     doInBackground
    -0.59
    ('--
    -0.57
    exitRule
    -0.56
    ChildScrollView
    -0.55
    ekš
    -0.54
    POSITIVE LOGITS
     $|
    1.05
    ]|
    0.98
    +|
    0.97
    .|
    0.97
     $|\
    0.97
    $|
    0.94
    -|
    0.94
    {|
    0.86
     |
    0.86
     |-
    0.86
    Act Density 0.200%

    No Known Activations