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

    Neuronpedia

    INDEX
    Explanations

    clock signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laborales
    0.46
     reconstructing
    0.44
     lab
    0.43
     staple
    0.42
     on
    0.41
    куда
    0.41
     reconstructions
    0.40
    Rustic
    0.40
    ў
    0.39
     reconstructed
    0.39
    POSITIVE LOGITS
    셈
    0.44
     çizg
    0.44
    ത്രം
    0.43
    ધન
    0.43
     şekilde
    0.42
    하세요
    0.42
     श्रेणी
    0.41
    埃
    0.41
    萨
    0.41
    薩
    0.41
    Act Density 0.000%

    No Known Activations