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

    Neuronpedia

    INDEX
    Explanations

    years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.75
    ের
    0.65
    5
    0.63
    ারে
    0.60
    ={()
    0.59
    yCoordinate
    0.58
    {
    0.58
    orkan
    0.57
     personnalité
    0.57
    aż
    0.56
    POSITIVE LOGITS
    ק
    0.64
    ש
    0.62
     பாம்பு
    0.58
     పోలీసులు
    0.57
     '
    0.56
    ח
    0.56
     اصل
    0.54
     जोरदार
    0.54
     언
    0.53
     బి
    0.53
    Act Density 0.002%

    No Known Activations