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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choices
    -0.07
     elective
    -0.06
     Choices
    -0.06
     Sequ
    -0.06
     Cou
    -0.06
    four
    -0.06
    Best
    -0.06
    False
    -0.06
    ��
    -0.06
    uracion
    -0.06
    POSITIVE LOGITS
    .clock
    0.08
    ENSIONS
    0.07
    복지
    0.07
     yoksa
    0.06
     зміст
    0.06
     amateurs
    0.06
    ILTER
    0.06
    .frames
    0.06
     家
    0.06
    inyin
    0.06
    Act Density 0.064%

    No Known Activations