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

    Neuronpedia

    INDEX
    Explanations

    SQL code snippets

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     most
    -1.59
    Most
    -1.43
     Most
    -1.40
    most
    -1.26
     MOST
    -1.16
    MOST
    -1.05
     moſt
    -0.92
     moft
    -0.90
     meest
    -0.68
     معظم
    -0.62
    POSITIVE LOGITS
    prüche
    0.59
     referenties
    0.59
    HttpFoundation
    0.54
     확인함
    0.52
     []).
    0.51
    istus
    0.49
    spunkt
    0.49
    المناصب
    0.48
    VERTISEMENT
    0.47
     inoxydable
    0.47
    Act Density 0.466%

    No Known Activations