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

    Neuronpedia

    INDEX
    Explanations

    layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    億
    -0.07
     Hash
    -0.07
     mpfr
    -0.07
    (SQL
    -0.06
     APC
    -0.06
     Georgian
    -0.06
     odor
    -0.06
     müz
    -0.06
     키
    -0.06
    enerima
    -0.06
    POSITIVE LOGITS
    ighbours
    0.07
    rina
    0.07
    Rachel
    0.07
    illed
    0.06
    zew
    0.06
     renewables
    0.06
     './
    0.06
    guards
    0.06
    Sm
    0.06
     mother
    0.06
    Act Density 0.005%

    No Known Activations