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

    Neuronpedia

    INDEX
    Explanations

    final draft destruction sip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     két
    0.43
     ê
    0.39
     दुप
    0.37
    )[:
    0.37
     precedenti
    0.37
     pistols
    0.36
     fark
    0.36
    Django
    0.36
     Fáb
    0.35
     démarrage
    0.35
    POSITIVE LOGITS
    ंजी
    0.44
    算的
    0.40
     चाहिँ
    0.40
    ordable
    0.39
     Polynesian
    0.38
     популя
    0.37
    agc
    0.36
    separatedBy
    0.36
    ßen
    0.35
    远远
    0.35
    Act Density 0.001%

    No Known Activations