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

    Neuronpedia

    INDEX
    Explanations

    matrix and vector notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ួត
    0.41
     Tanık
    0.38
    इंदौर
    0.38
    முருக
    0.38
    ettiva
    0.38
     Dill
    0.37
     europeo
    0.37
     signific
    0.37
    ierge
    0.37
    美品
    0.36
    POSITIVE LOGITS
    pmatrix
    0.80
    bmatrix
    0.72
     determinant
    0.55
    BS
    0.52
    bs
    0.52
    bsch
    0.50
     matrix
    0.49
    ⎛
    0.46
    Determ
    0.45
    ⎤
    0.45
    Act Density 0.004%

    No Known Activations