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

    Neuronpedia

    INDEX
    Explanations

    });

    np_max-act · gemini-2.0-flash

    This neuron responds to code indentation/whitespace (sequences of spaces or tabs) rather than actual words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Yas
    -0.06
    _alpha
    -0.06
    点
    -0.06
     yurt
    -0.06
     škol
    -0.06
    _embedding
    -0.06
    奇
    -0.06
     drv
    -0.06
    Folders
    -0.06
     symb
    -0.06
    POSITIVE LOGITS
     Investor
    0.06
    overflow
    0.06
     XBOOLE
    0.06
    URL
    0.06
    ],'
    0.06
    
    0.06
    apk
    0.06
    ++;
↵
    0.06
    RectTransform
    0.06
     NONINFRINGEMENT
    0.06
    Act Density 0.015%

    No Known Activations