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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꗥ
    0.57
    他人
    0.47
     marriages
    0.47
     irland
    0.46
     medicines
    0.46
     orchids
    0.46
     юби
    0.46
    hko
    0.46
    ्युअर
    0.46
     philanth
    0.45
    POSITIVE LOGITS
    #
    0.87
    $$\
    0.86
    $\
    0.74
    *\
    0.64
    II
    0.63
    *
    0.61
    \\
    0.58
    \
    0.58
    \[
    0.55
     \\
    0.53
    Act Density 0.001%

    No Known Activations