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

    Neuronpedia

    INDEX
    Explanations

    say " or '

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DS
    0.44
     DS
    0.42
     XK
    0.40
    TestSuite
    0.40
    Ca
    0.39
    的面
    0.37
    nsec
    0.37
    dosage
    0.36
    栃
    0.36
     நாளில்
    0.36
    POSITIVE LOGITS
    chelles
    0.47
     }-\
    0.37
    hii
    0.36
    érien
    0.36
    árny
    0.36
     }^{-
    0.35
     necrosis
    0.35
     اذا
    0.35
    urbation
    0.35
     सुने
    0.35
    Act Density 0.000%

    No Known Activations