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

    Neuronpedia

    INDEX
    Explanations

    retrieved from or accessed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ുവരി
    0.40
     decays
    0.38
    ፈላጊ
    0.37
     Sublime
    0.36
    ராட்ச
    0.36
    ட்ரா
    0.35
     goû
    0.35
     setTo
    0.35
     orthogonal
    0.35
     diffusing
    0.34
    POSITIVE LOGITS
     Retrieved
    0.82
     retrieved
    0.75
     cited
    0.67
     Accessed
    0.63
     accessed
    0.62
     अभिगमन
    0.60
     Diakses
    0.60
    Accessed
    0.59
     Cited
    0.57
    cited
    0.56
    Act Density 0.004%

    No Known Activations