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

    Neuronpedia

    INDEX
    Explanations

    experimental and empirical probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    主要的
    0.40
    ера
    0.38
    Games
    0.38
     drum
    0.37
     competing
    0.37
     motorized
    0.36
     প্রতিযোগ
    0.36
     games
    0.36
    ensis
    0.36
    Globe
    0.35
    POSITIVE LOGITS
     Covering
    0.49
     couv
    0.49
     Empirical
    0.46
     covering
    0.46
     empirical
    0.45
     Experimental
    0.45
     Covers
    0.45
     voisins
    0.45
     experimental
    0.44
     dozen
    0.44
    Act Density 0.005%

    No Known Activations