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

    Neuronpedia

    INDEX
    Explanations

    find matching items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     möglichen
    0.34
    𝔦
    0.33
    трима
    0.31
    癃
    0.31
    樖
    0.31
    軛
    0.30
    టర్
    0.30
    ँग्रेस
    0.30
     센
    0.30
     coloquei
    0.30
    POSITIVE LOGITS
    a
    0.40
    6
    0.38
    7
    0.35
    8
    0.34
     tears
    0.34
    at
    0.33
     over
    0.32
     at
    0.32
    9
    0.32
    ↵↵
    0.32
    Act Density 0.000%

    No Known Activations