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

    Neuronpedia

    INDEX
    Explanations

    code delimiters and diverse content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    歎
    0.39
    嘆
    0.38
     ಮಾತ
    0.38
    渽
    0.36
     }+
    0.35
    enee
    0.35
     punches
    0.34
    ௭
    0.34
     त्याची
    0.34
     wattage
    0.34
    POSITIVE LOGITS
     Tourism
    0.42
     Kitchen
    0.41
    कैसे
    0.39
    GFP
    0.39
     Buff
    0.38
    Buffer
    0.37
    ங்களிலிருந்து
    0.37
    şk
    0.37
    Buf
    0.37
     Buffer
    0.37
    Act Density 0.001%

    No Known Activations