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

    Neuronpedia

    INDEX
    Explanations

    name fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apoptosis
    0.53
     physiologically
    0.48
     thermodynamics
    0.48
     cuant
    0.47
     antioxid
    0.47
     vessie
    0.46
     angulis
    0.45
     quantization
    0.44
     cakkh
    0.44
     quanta
    0.43
    POSITIVE LOGITS
     name
    1.16
     names
    1.11
     Name
    1.04
     Names
    1.04
     naming
    1.00
    名稱
    0.99
    姓名
    0.98
    name
    0.98
     имена
    0.95
    名称
    0.94
    Act Density 0.255%

    No Known Activations