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

    Neuronpedia

    INDEX
    Explanations

    commas and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    雖
    0.29
     ledger
    0.24
     radios
    0.23
     eax
    0.23
     flee
    0.23
     protezione
    0.23
     हालांकि
    0.23
     všet
    0.23
     pests
    0.22
     provenant
    0.22
    POSITIVE LOGITS
    उस
    0.28
    then
    0.27
    these
    0.27
    ção
    0.27
    there
    0.26
    we
    0.26
    this
    0.26
    ócio
    0.26
    that
    0.25
    here
    0.25
    Act Density 0.382%

    No Known Activations