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

    Neuronpedia

    INDEX
    Explanations

    not mentioned or missing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setzung
    0.44
    stellung
    0.43
     Vorstellung
    0.42
     aandacht
    0.41
    fields
    0.40
    ück
    0.40
    rovers
    0.40
    ירים
    0.39
    ujemo
    0.39
     zbior
    0.38
    POSITIVE LOGITS
    ร
    0.47
     ஆறு
    0.46
     सुधार
    0.45
     безу
    0.45
     แล้ว
    0.43
    0.42
     Volumes
    0.42
    toNumber
    0.42
    述べ
    0.42
    ㎖
    0.42
    Act Density 0.002%

    No Known Activations