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

    Neuronpedia

    INDEX
    Explanations

    **machine** `/` **conductivity** `/` **true**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ansa
    0.50
    tag
    0.49
    ingar
    0.49
    appears
    0.48
    targeting
    0.48
    apparent
    0.47
    inflation
    0.45
     appears
    0.44
    very
    0.44
    arith
    0.44
    POSITIVE LOGITS
     Emperor
    0.46
     Latitude
    0.43
     Emperors
    0.43
     véh
    0.43
     IRB
    0.42
     JTextField
    0.42
     desemb
    0.41
    Latitude
    0.41
     Jawaharlal
    0.41
    هاي
    0.39
    Act Density 0.000%

    No Known Activations