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

    Neuronpedia

    INDEX
    Explanations

    programs :**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     go
    0.46
     Hitler
    0.44
     विकल्प
    0.43
    თვის
    0.42
    ჯგუფი
    0.42
     हिटलर
    0.42
     Nazi
    0.42
    ebb
    0.41
     demoral
    0.41
     concurred
    0.40
    POSITIVE LOGITS
     संयोजक
    0.45
     coordinadora
    0.44
     bioquímica
    0.42
    濯
    0.42
     struktur
    0.39
    ordes
    0.39
     anggota
    0.39
     الفر
    0.39
    ங்கிணை
    0.39
    aniyam
    0.39
    Act Density 0.003%

    No Known Activations