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

    Neuronpedia

    INDEX
    Explanations

    Code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ze
    -0.08
     darker
    -0.07
    ycz
    -0.07
    *I
    -0.07
     Claus
    -0.06
    qli
    -0.06
     Ä
    -0.06
    -0.06
    *M
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     tires
    0.07
     Redux
    0.07
    .sel
    0.07
     kinds
    0.06
    ۱۹
    0.06
    ặn
    0.06
     garbage
    0.06
    .sprites
    0.06
    ñana
    0.06
     حس
    0.06
    Act Density 0.000%

    No Known Activations