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

    Neuronpedia

    INDEX
    Explanations

    slot machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    1.30
    ;
    1.29
    ق
    1.26
    ים
    1.24
    ك
    1.21
    는
    1.18
    us
    1.17
    ر
    1.17
    是
    1.16
    కు
    1.16
    POSITIVE LOGITS
    to
    1.62
     slots
    1.32
     aument
    1.20
     montar
    1.19
     completar
    1.17
     ordenar
    1.11
     enviar
    1.09
     Slots
    1.06
     সময়ে
    1.04
     ampli
    1.04
    Act Density 0.002%

    No Known Activations