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

    Neuronpedia

    INDEX
    Explanations

    computational programming environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Appodeal
    0.42
    Opinion
    0.41
     мнение
    0.40
    imonials
    0.40
    വില്‍
    0.40
    สต
    0.40
     Tonight
    0.39
    Billy
    0.39
     Mechanic
    0.38
     Auctions
    0.37
    POSITIVE LOGITS
     scipy
    0.47
     ansatz
    0.47
     tensor
    0.47
    pytorch
    0.46
     extract
    0.45
     MATLAB
    0.44
     subspace
    0.43
     tensorflow
    0.43
     glial
    0.42
     separable
    0.42
    Act Density 0.000%

    No Known Activations