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

    Neuronpedia

    INDEX
    Explanations

    German names and compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stead
    0.44
    combe
    0.41
     compositional
    0.40
     Another
    0.39
    adiyah
    0.39
    as
    0.39
    iD
    0.39
    доне
    0.38
    ாப்
    0.38
     Fian
    0.37
    POSITIVE LOGITS
    wein
    0.74
    reich
    0.71
    bauer
    0.70
    schein
    0.70
    weis
    0.70
    мец
    0.69
     reich
    0.67
     unserer
    0.66
    wasser
    0.66
    auer
    0.65
    Act Density 0.004%

    No Known Activations