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

    Neuronpedia

    INDEX
    Explanations

    X-ray Fish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Obligations
    0.37
     adsorb
    0.37
     referrerpolicy
    0.37
     igen
    0.37
     Numpy
    0.36
     deriv
    0.36
     Crops
    0.36
    കൾ
    0.35
     Tensorflow
    0.35
    ֶ
    0.35
    POSITIVE LOGITS
     excepting
    0.45
    Quanto
    0.44
    uar
    0.38
    neath
    0.38
     reindeer
    0.37
    Past
    0.37
    Lady
    0.37
    Insect
    0.37
    een
    0.36
     quanto
    0.36
    Act Density 0.001%

    No Known Activations