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

    Neuronpedia

    INDEX
    Explanations

    fixing problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ber
    -0.07
     ứng
    -0.06
     چون
    -0.06
     killer
    -0.06
     cone
    -0.06
     meddling
    -0.06
     Ber
    -0.06
    ezier
    -0.06
    ond
    -0.06
     cartel
    -0.06
    POSITIVE LOGITS
    landscape
    0.06
    (EXIT
    0.06
     přisp
    0.06
    ＿＿＿＿＿＿＿＿
    0.06
    '];
    0.06
     apologise
    0.06
     spotting
    0.06
    October
    0.06
    <B
    0.06
     празд
    0.06
    Act Density 0.098%

    No Known Activations