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

    Neuronpedia

    INDEX
    Explanations

    male given names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ദൈവ
    0.89
    ়
    0.75
     ভগব
    0.73
    Fc
    0.69
    缟
    0.69
    သေး
    0.68
    ন্তু
    0.67
    Һ
    0.65
     NgModule
    0.65
    ivesse
    0.64
    POSITIVE LOGITS
     Josh
    3.26
     Jason
    3.22
     Michael
    3.18
     Brian
    3.18
     Steve
    3.17
     David
    3.17
     Andrew
    3.15
     Mike
    3.09
     Kevin
    3.09
     Dave
    3.06
    Act Density 0.338%

    No Known Activations