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

    Neuronpedia

    INDEX
    Explanations

    manage permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simple
    0.44
    0.43
     geometrically
    0.43
     ශ
    0.42
    covite
    0.41
     przyj
    0.40
     Mosk
    0.40
    nés
    0.40
     Ech
    0.40
    嫘
    0.40
    POSITIVE LOGITS
     necesitas
    0.55
    λή
    0.49
     acusado
    0.46
     адміністра
    0.46
    ญี่ปุ่น
    0.45
     можа
    0.45
    ujący
    0.44
     ਕੀਤਾ
    0.44
     छोड़
    0.44
     nCmdShow
    0.44
    Act Density 0.001%

    No Known Activations