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

    Neuronpedia

    INDEX
    Explanations

    duet and Manuel Miranda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    year
    0.75
    <0x80>
    0.74
    หวาน
    0.66
    '
    0.64
    toDate
    0.63
     sebagainya
    0.62
    pecific
    0.61
     estará
    0.60
    tais
    0.60
     우
    0.59
    POSITIVE LOGITS
     for
    0.88
     opposites
    0.61
     clap
    0.61
    O
    0.59
     BOD
    0.58
    قي
    0.57
     by
    0.57
     blades
    0.56
    d
    0.55
     ones
    0.55
    Act Density 0.005%

    No Known Activations