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

    Neuronpedia

    INDEX
    Explanations

    popularity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Imp
    -0.07
     đ
    -0.06
     nano
    -0.06
    έργ
    -0.06
     сосуд
    -0.06
    ⠀⠀
    -0.06
    ='';↵
    -0.06
    ////////////////////////////////////////////////////////////////
    -0.06
     faculty
    -0.06
     вари
    -0.06
    POSITIVE LOGITS
     popularity
    0.12
    されている
    0.06
     rozsah
    0.06
     gdzie
    0.06
    左
    0.06
    jax
    0.06
    (cos
    0.06
    _ta
    0.06
     emerges
    0.06
     [(
    0.06
    Act Density 0.016%

    No Known Activations