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

    Neuronpedia

    INDEX
    Explanations

    Tiffany

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —to
    -0.08
    .hadoop
    -0.07
    So
    -0.07
     Ø
    -0.07
     Op
    -0.07
     Dead
    -0.07
     row
    -0.06
     To
    -0.06
     believes
    -0.06
    Last
    -0.06
    POSITIVE LOGITS
     Jacqueline
    0.08
     Jessica
    0.07
     Gir
    0.07
    ء
    0.07
    �
    0.07
    玉
    0.07
     Manson
    0.07
    .twitch
    0.07
    orgetown
    0.07
     Jackie
    0.07
    Act Density 0.048%

    No Known Activations