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

    Neuronpedia

    INDEX
    Explanations

    component rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இவ்வ
    0.75
    +
    0.65
     دیکھتے
    0.60
    /
    0.58
     Byl
    0.58
     Transient
    0.57
    *
    0.54
    S
    0.54
     повышен
    0.54
    perity
    0.53
    POSITIVE LOGITS
    很有
    1.07
    🚽
    0.95
     bathroom
    0.95
    🕘
    0.92
    🕚
    0.91
    🕤
    0.91
    🛀
    0.90
     Itália
    0.90
     രണ്ട്
    0.90
    ⣀
    0.90
    Act Density 0.000%

    No Known Activations