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

    Neuronpedia

    INDEX
    Explanations

    weighing pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mat
    0.41
    Dun
    0.41
     Dun
    0.41
     Mat
    0.40
     കൂടുതൽ
    0.39
     ڈ
    0.39
    只会
    0.39
     Bor
    0.38
     කො
    0.38
     secondaire
    0.38
    POSITIVE LOGITS
    \}^{
    0.44
    व्यव
    0.39
     मश
    0.39
    reflective
    0.39
    oths
    0.38
    нија
    0.38
    eared
    0.38
    nbhd
    0.37
     reflective
    0.36
    短
    0.36
    Act Density 0.000%

    No Known Activations