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

    Neuronpedia

    INDEX
    Explanations

    5, 1, 6, 5, 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nearly
    0.55
    ❐
    0.51
     quasi
    0.49
     (!)
    0.49
    🔻
    0.48
    (!)
    0.48
     almost
    0.48
     virtually
    0.48
    ட்டர்
    0.47
    孃
    0.46
    POSITIVE LOGITS
    5
    1.05
    1
    0.93
    6
    0.89
    3
    0.89
    2
    0.85
    4
    0.84
    7
    0.83
     vijf
    0.82
     ५
    0.82
    ５
    0.82
    Act Density 0.482%

    No Known Activations