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

    Neuronpedia

    INDEX
    Explanations

    floating point numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Legislative
    0.84
     harry
    0.84
     Harry
    0.82
     Charter
    0.81
     Ridd
    0.78
    Harry
    0.77
     Palace
    0.75
     Security
    0.75
     الأمن
    0.74
     граф
    0.73
    POSITIVE LOGITS
    float
    1.76
     float
    1.71
    Float
    1.66
     parseFloat
    1.49
    parseFloat
    1.48
     Float
    1.40
     floating
    1.40
     floats
    1.39
    FLOAT
    1.37
     calculating
    1.32
    Act Density 1.300%

    No Known Activations