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

    Neuronpedia

    INDEX
    Explanations

    birth dates and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     centrum
    -0.76
    juje
    -0.74
     Company
    -0.71
    leve
    -0.71
    oprote
    -0.70
    rister
    -0.69
    meno
    -0.68
    ሜ
    -0.68
    ϵ
    -0.68
    macs
    -0.67
    POSITIVE LOGITS
     born
    1.03
     urodz
    0.98
    Born
    0.94
    დ
    0.91
     raised
    0.90
     birth
    0.88
     birthplace
    0.83
    ättä
    0.82
    Agencies
    0.81
    Caprio
    0.79
    Act Density 0.079%

    No Known Activations