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

    Neuronpedia

    INDEX
    Explanations

    avoid robotic phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powodu
    0.44
     ه
    0.43
     crop
    0.42
    😆
    0.41
     Finance
    0.41
     对象
    0.41
     occasione
    0.40
     Crop
    0.39
    :“
    0.38
     kunde
    0.38
    POSITIVE LOGITS
     असाल
    0.47
    ர்க்
    0.45
    alti
    0.44
    iply
    0.44
     डाउनलोड
    0.43
    ጠቀ
    0.43
    included
    0.42
    accessible
    0.42
     दशमलव
    0.42
    ஔ
    0.41
    Act Density 0.000%

    No Known Activations