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

    Neuronpedia

    INDEX
    Explanations

    isn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [n
    -0.06
     wides
    -0.06
     север
    -0.06
     cih
    -0.06
     Jog
    -0.06
    /[
    -0.06
     Patt
    -0.06
    <w
    -0.06
     şun
    -0.06
    .unlock
    -0.06
    POSITIVE LOGITS
    rina
    0.07
    interactive
    0.07
     　 　 　 　 　 　
    0.07
     flick
    0.06
    ﾆﾆﾆﾆ
    0.06
     повітря
    0.06
     powerless
    0.06
    入り
    0.06
    66
    0.06
    95
    0.06
    Act Density 0.001%

    No Known Activations