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

    Neuronpedia

    INDEX
    Explanations

    update status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financed
    0.47
    sales
    0.46
    irs
    0.45
     visitors
    0.45
    ville
    0.44
    the
    0.43
     employers
    0.43
     government
    0.42
     municipal
    0.42
     sales
    0.42
    POSITIVE LOGITS
    讠
    0.49
     conséquence
    0.47
     posteriormente
    0.42
     dimana
    0.42
     می‌دهد
    0.42
     cervix
    0.41
     डेफिनेशन
    0.41
     اللغة
    0.41
     regiones
    0.41
     anschließend
    0.41
    Act Density 0.001%

    No Known Activations