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

    Neuronpedia

    INDEX
    Explanations

    provided "as is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sessão
    0.42
     sappiamo
    0.41
    OLOGIA
    0.40
     conocemos
    0.40
    LPTMR
    0.39
    연구
    0.39
     pasando
    0.39
    iciencia
    0.38
    ಷ
    0.38
    modulo
    0.38
    POSITIVE LOGITS
     provided
    0.54
     supplied
    0.44
     (!
    0.42
     offered
    0.42
    提供的
    0.40
     glist
    0.40
     제공
    0.39
     Chest
    0.39
     предоставля
    0.38
     arrived
    0.38
    Act Density 0.001%

    No Known Activations