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

    Neuronpedia

    INDEX
    Explanations

    addition problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _____
    0.84
     Nepal
    0.82
    ______
    0.82
    ____
    0.81
    ________
    0.81
    _______
    0.80
     Bangkok
    0.79
    __________
    0.78
    Nepal
    0.77
     cuộc
    0.77
    POSITIVE LOGITS
    gca
    0.73
    rotechn
    0.71
     +
    0.69
     profitable
    0.65
    ্পনিক
    0.65
    specialchars
    0.62
    .+
    0.61
    见的
    0.61
    !
    0.60
    த்தான்
    0.60
    Act Density 0.028%

    No Known Activations