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

    Neuronpedia

    INDEX
    Explanations

    references to Whitman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.88
    t
    0.76
     Brunei
    0.70
    funcionario
    0.68
    y
    0.67
    aii
    0.67
    c
    0.66
    g
    0.66
    வ்
    0.64
     scorpion
    0.63
    POSITIVE LOGITS
    ও
    0.86
    在
    0.82
    도
    0.80
    も
    0.74
     in
    0.72
    데
    0.68
    ”
    0.66
    在我们
    0.62
    那我們
    0.61
    ,​
    0.61
    Act Density 0.001%

    No Known Activations