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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hy
    -0.07
     Hemisphere
    -0.06
    _VAR
    -0.06
    weigh
    -0.06
     meaningless
    -0.06
     Westminster
    -0.06
     Universal
    -0.06
     Damien
    -0.06
     HelloWorld
    -0.06
    好了
    -0.06
    POSITIVE LOGITS
    713
    0.07
    .listener
    0.07
     undergrad
    0.06
    ocked
    0.06
    eka
    0.06
     آسیاب
    0.06
     menn
    0.06
    >".$
    0.06
    =mysqli
    0.06
    iya
    0.06
    Act Density 0.036%

    No Known Activations