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

    Neuronpedia

    INDEX
    Explanations

    React styled components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    0.43
    astype
    0.42
     `
    0.41
    let
    0.40
     >
    0.39
    dir
    0.38
    bigg
    0.38
     <>
    0.38
     simplic
    0.38
    gg
    0.37
    POSITIVE LOGITS
     YOUNG
    0.45
     अरुण
    0.42
    रूम
    0.40
    ंची
    0.39
    Young
    0.38
     Warranty
    0.38
     सोया
    0.38
     Routledge
    0.37
     النج
    0.37
    Handle
    0.37
    Act Density 0.001%

    No Known Activations