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

    Neuronpedia

    INDEX
    Explanations

    this to taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڎ
    0.46
    i
    0.43
    Persistent
    0.42
     Persistent
    0.41
    ниць
    0.40
     तकलीफ
    0.40
     ପ
    0.39
     hợp
    0.39
    无效
    0.39
     в
    0.38
    POSITIVE LOGITS
     σχέ
    0.45
    これを
    0.44
    phol
    0.44
    今回の
    0.43
    agio
    0.43
     reviews
    0.43
    FUL
    0.43
    డని
    0.42
     this
    0.42
     ஸ்
    0.42
    Act Density 0.000%

    No Known Activations