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

    Neuronpedia

    INDEX
    Explanations

    fact sheet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.64
    l
    0.60
    le
    0.55
     disrupt
    0.53
     be
    0.53
     use
    0.51
    an
    0.50
    as
    0.49
    lo
    0.49
    c
    0.48
    POSITIVE LOGITS
    ಿಯನ್ನು
    0.57
    Movies
    0.53
    ಕೊ
    0.53
    .??.??"]
    0.53
     playerName
    0.52
    ının
    0.51
    🏙
    0.51
    ameen
    0.50
    𝜆
    0.50
    <unused86>
    0.49
    Act Density 0.000%

    No Known Activations