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

    Neuronpedia

    INDEX
    Explanations

    Javascript code

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of JavaScript library/plugin filenames (“.js”) often alongside version numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Heath
    -0.06
    (Test
    -0.06
    <O
    -0.06
    .optional
    -0.06
    .Quantity
    -0.06
    prefs
    -0.06
    -yard
    -0.06
    ."+
    -0.06
    _ros
    -0.06
    .discount
    -0.06
    POSITIVE LOGITS
     -->↵↵↵
    0.08
    aurant
    0.07
     entrev
    0.06
     -->
↵
↵
    0.06
     编辑
    0.06
     femin
    0.06
    };↵↵↵
    0.06
     nez
    0.06
     mysql
    0.06
    属于
    0.06
    Act Density 0.004%

    No Known Activations