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

    Neuronpedia

    INDEX
    Explanations

    connectors after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h4>
    0.24
    </h3>
    0.23
    ท
    0.23
     असंख्य
    0.23
     với
    0.22
    不僅
    0.22
     be
    0.22
    ម្បី
    0.22
    عت
    0.21
    如今
    0.21
    POSITIVE LOGITS
    in
    0.28
    2
    0.27
    of
    0.26
     disenfranch
    0.26
    d
    0.26
     একটা
    0.26
    at
    0.25
     bisog
    0.24
     endanger
    0.24
     എന്നാണ്
    0.24
    Act Density 1.544%

    No Known Activations