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

    Neuronpedia

    INDEX
    Explanations

    keys and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elytris
    0.41
     terceiro
    0.39
     biliary
    0.37
     IPython
    0.37
    ప్త
    0.37
     bessere
    0.37
     movimenti
    0.37
     selten
    0.36
    ິ່ງ
    0.36
     divulgação
    0.36
    POSITIVE LOGITS
    name
    0.47
    title
    0.44
    ini
    0.37
    set
    0.37
     name
    0.37
    type
    0.36
    Type
    0.35
    hi
    0.34
    ujian
    0.34
     عنوان
    0.33
    Act Density 0.139%

    No Known Activations