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

    Neuronpedia

    INDEX
    Explanations

    understanding the why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esforços
    0.54
     sabiduría
    0.48
     possibilidade
    0.47
     दाब
    0.47
     possíveis
    0.47
     SoaException
    0.46
    squre
    0.45
     plantes
    0.45
     tarses
    0.45
    प्त
    0.44
    POSITIVE LOGITS
     The
    0.58
     I
    0.51
     Information
    0.49
    ,
    0.48
     What
    0.46
     Date
    0.46
     Fields
    0.46
     Email
    0.45
     Math
    0.44
     Anonymous
    0.44
    Act Density 0.000%

    No Known Activations