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

    Neuronpedia

    INDEX
    Explanations

    depends, varies, condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.29
    ',
    0.28
    。
    0.26
    ۔
    0.26
    );
    0.25
    ，
    0.24
    ।
    0.24
    ().
    0.24
    (),
    0.24
    ",
    0.23
    POSITIVE LOGITS
     είναι
    0.29
     differs
    0.29
     varies
    0.28
     está
    0.27
     fluctuates
    0.25
     rimane
    0.25
     diffère
    0.25
     transcends
    0.24
     depender
    0.24
     continúa
    0.23
    Act Density 0.824%

    No Known Activations