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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    751
    -0.07
    prt
    -0.06
     trov
    -0.06
    fname
    -0.06
    מ
    -0.06
    KO
    -0.06
    M
    -0.06
     lubric
    -0.06
    ф
    -0.06
    al
    -0.06
    POSITIVE LOGITS
     =$
    0.07
    .***
    0.07
    腦
    0.07
    ${
    0.06
    ('//*[@
    0.06
     veya
    0.06
     Swal
    0.06
     reserv
    0.06
    (sprite
    0.06
     frowned
    0.06
    Act Density 0.111%

    No Known Activations