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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     생성
    -0.08
     مخصوص
    -0.07
    وة
    -0.06
    $out
    -0.06
     Tanks
    -0.06
    File
    -0.06
    Met
    -0.06
     Chester
    -0.06
     symbolic
    -0.06
     Software
    -0.06
    POSITIVE LOGITS
     Ανα
    0.07
    ITHUB
    0.06
     nieu
    0.06
     ním
    0.06
    AGMA
    0.06
    .hl
    0.06
    _almost
    0.06
     tez
    0.05
    .nick
    0.05
    -Trump
    0.05
    Act Density 0.048%

    No Known Activations