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

    Neuronpedia

    INDEX
    Explanations

    names of children and relatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Caleb
    0.50
     grandsons
    0.49
     Jonathan
    0.48
     محسن
    0.48
     Bethany
    0.47
    Nathan
    0.47
     Joshua
    0.46
    Sarah
    0.45
     ethan
    0.44
    Joshua
    0.44
    POSITIVE LOGITS
     tot
    0.43
    Tot
    0.42
    ocr
    0.42
     Tot
    0.41
    Unix
    0.40
     Lux
    0.40
    lux
    0.39
     ++;
    0.39
    Banks
    0.39
    ix
    0.38
    Act Density 0.003%

    No Known Activations