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

    Neuronpedia

    INDEX
    Explanations

    random integer range assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molar
    0.68
     millimeters
    0.64
    /=
    0.64
    0
    0.64
     `
    0.62
     porosity
    0.62
     `./
    0.62
     millimeter
    0.62
     `$
    0.62
    $
    0.62
    POSITIVE LOGITS
    多人
    0.74
     Erkennt
    0.63
     кого
    0.63
    कर्ष
    0.63
    Người
    0.61
    歉
    0.61
     mucha
    0.60
     sabiduría
    0.60
     শক্ত
    0.60
    ształ
    0.59
    Act Density 0.040%

    No Known Activations