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

    Neuronpedia

    INDEX
    Explanations

    the ride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cookie
    1.12
     Fulton
    1.08
     CID
    1.03
    Cookie
    1.01
    CSS
    1.01
     cookies
    1.00
     cookie
    1.00
    閃
    0.99
     BCC
    0.98
    ET
    0.98
    POSITIVE LOGITS
     x
    1.79
    x
    1.78
    xRt
    1.42
    xz
    1.35
    xA
    1.27
    xB
    1.25
    yx
    1.21
    xF
    1.19
    bx
    1.18
    xan
    1.18
    Act Density 0.615%

    No Known Activations