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

    Neuronpedia

    INDEX
    Explanations

    Java/Spring autowiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ーン
    0.41
     prof
    0.39
     exclusiva
    0.39
     Heavy
    0.38
    autog
    0.38
     COURSE
    0.37
     Faculdade
    0.37
     effets
    0.36
     meest
    0.36
     lightest
    0.36
    POSITIVE LOGITS
    Website
    0.40
    website
    0.39
    曰
    0.38
    Available
    0.38
    EOL
    0.37
    &)
    0.37
    Bước
    0.37
    Salir
    0.36
    Aye
    0.36
    engkapi
    0.35
    Act Density 0.001%

    No Known Activations