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

    Neuronpedia

    INDEX
    Explanations

    citation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potenza
    0.43
     pooling
    0.39
     limpeza
    0.39
     deterrence
    0.38
     problemi
    0.38
     abatement
    0.38
     voh
    0.38
    Pip
    0.38
     krav
    0.37
     hvis
    0.37
    POSITIVE LOGITS
     опубликован
    0.41
    리에
    0.39
    {\'
    0.38
    赚
    0.37
    arları
    0.37
     сообщает
    0.36
    owości
    0.36
    进士
    0.36
    ésia
    0.36
     странице
    0.35
    Act Density 0.007%

    No Known Activations