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

    Neuronpedia

    INDEX
    Explanations

    code artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    90
    -0.07
     Direction
    -0.07
    .Ignore
    -0.06
    .contentView
    -0.06
     atd
    -0.06
    _arr
    -0.06
    .keyboard
    -0.06
     interpreted
    -0.06
     skull
    -0.06
    	byte
    -0.06
    POSITIVE LOGITS
    eventType
    0.06
     sourceMappingURL
    0.06
    ��
    0.06
    raise
    0.06
    clinic
    0.06
    (metrics
    0.06
    (pg
    0.06
     запис
    0.06
    adresse
    0.06
    ");}↵
    0.06
    Act Density 0.017%

    No Known Activations