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

    Neuronpedia

    INDEX
    Explanations

    life filled or life had

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     krv
    0.90
    ión
    0.83
    puede
    0.82
    murder
    0.77
    𝒽
    0.76
    Measurements
    0.75
    cvtColor
    0.75
    aughty
    0.75
     сега
    0.74
    ainty
    0.74
    POSITIVE LOGITS
     academia
    0.81
    รษฐกิจ
    0.78
     dioxide
    0.75
     процессо
    0.71
    orschungs
    0.68
     부터
    0.68
     extensively
    0.67
     reta
    0.67
     ethic
    0.66
     कोणताही
    0.66
    Act Density 0.000%

    No Known Activations