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

    Neuronpedia

    INDEX
    Explanations

    visualize code and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apathy
    0.47
    𝗖
    0.45
     colore
    0.44
     màu
    0.44
     און
    0.43
    𝗦
    0.43
     berwarna
    0.42
     ischa
    0.42
     nutrients
    0.42
     Bây
    0.42
    POSITIVE LOGITS
    generators
    0.44
    jectory
    0.43
    ameras
    0.42
    arb
    0.42
    член
    0.42
    impose
    0.41
    att
    0.41
     लॉग
    0.41
    amer
    0.40
    이어
    0.40
    Act Density 0.012%

    No Known Activations