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

    Neuronpedia

    INDEX
    Explanations

    citations or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fortunately
    0.98
     wk
    0.97
    fully
    0.96
    to
    0.93
     flound
    0.92
    x
    0.91
    p
    0.91
    cute
    0.91
    g
    0.90
    当
    0.89
    POSITIVE LOGITS
     हुई
    0.99
    erne
    0.99
     Nummer
    0.95
     ちゃう
    0.93
     हुए
    0.91
    ocker
    0.87
    ร
    0.85
    sø
    0.85
     gevoel
    0.85
    يد
    0.85
    Act Density 0.000%

    No Known Activations