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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	gbc
    -0.07
    ╨
    -0.07
     fabulous
    -0.07
     tấn
    -0.07
    极具
    -0.07
    Enh
    -0.06
     jej
    -0.06
     squir
    -0.06
    &q
    -0.06
     Tube
    -0.06
    POSITIVE LOGITS
    生涯
    0.07
    banner
    0.07
     мн
    0.07
    csr
    0.07
    新华
    0.06
    assume
    0.06
    .gnu
    0.06
     hometown
    0.06
     אצל
    0.06
    🤴
    0.06
    Act Density 0.025%

    No Known Activations