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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chayin
    0.29
     Keci
    0.29
     Ecusson
    0.27
     Calyce
    0.26
    秝
    0.26
    िरपेक्ष
    0.26
    爌
    0.26
    urètre
    0.26
    cosec
    0.25
    ovariant
    0.25
    POSITIVE LOGITS
     G
    0.39
     T
    0.38
     B
    0.38
     F
    0.38
     W
    0.37
     S
    0.36
     M
    0.36
     Miller
    0.36
     J
    0.35
     Jones
    0.35
    Act Density 0.018%

    No Known Activations