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

    Neuronpedia

    INDEX
    Explanations

    coding constructs and library names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]
    0.30
     fragmentary
    0.27
     rather
    0.25
     Chief
    0.25
     Hens
    0.25
     patrons
    0.25
     authors
    0.24
     asserted
    0.24
     substantial
    0.24
     Collected
    0.24
    POSITIVE LOGITS
     ujian
    0.32
     residencial
    0.28
     упраж
    0.28
    Airbnb
    0.28
    Ꮡ
    0.28
    銀行
    0.27
     ejercicios
    0.27
    ات
    0.27
    电商
    0.27
     restoran
    0.27
    Act Density 0.001%

    No Known Activations