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

    Neuronpedia

    INDEX
    Explanations

    sofishticated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atuak
    0.41
    सीजी
    0.39
     न्यूमेर
    0.39
    ത്യാ
    0.38
    ვალ
    0.37
    ravés
    0.37
     verdadera
    0.36
     handheld
    0.36
     especializada
    0.36
     എത്ര
    0.35
    POSITIVE LOGITS
     prot
    0.45
    映
    0.45
     nơi
    0.42
    ్రో
    0.39
    렴
    0.39
    CHEM
    0.38
     brems
    0.38
     подро
    0.37
    〈
    0.37
    Empty
    0.37
    Act Density 0.002%

    No Known Activations