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

    Neuronpedia

    INDEX
    Explanations

    github.com urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ag
    0.31
    ir
    0.31
    ed
    0.29
    us
    0.28
    z
    0.28
    G
    0.26
    s
    0.26
    ay
    0.24
    ne
    0.24
    minton
    0.23
    POSITIVE LOGITS
     deniz
    0.20
     financeiros
    0.20
     a
    0.19
     (
    0.18
    क्यूमेंट
    0.18
     financieros
    0.18
     Mijn
    0.17
     yine
    0.17
     Elisabeth
    0.17
    </th>
    0.17
    Act Density 0.000%

    No Known Activations