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

    Neuronpedia

    INDEX
    Explanations

    numbered list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mogo
    0.89
    Mogo
    0.88
    ultimo
    0.87
     ultimate
    0.86
    ração
    0.83
     paramount
    0.82
     চতুর্থ
    0.82
     ultimo
    0.81
     ISZ
    0.79
     .......
    0.78
    POSITIVE LOGITS
    Usage
    0.89
     Usage
    0.85
    뇌
    0.77
    nd
    0.76
    ت
    0.73
    usage
    0.69
    脳
    0.69
     Became
    0.68
    then
    0.66
    二是
    0.66
    Act Density 0.000%

    No Known Activations