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

    Neuronpedia

    INDEX
    Explanations

    Hugging Face Spaces demos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acketing
    0.37
    branchNode
    0.36
     だっ
    0.36
     すぎ
    0.36
     ／
    0.35
    <0x15>
    0.35
     equivari
    0.35
    poetrylovers
    0.35
    വ്ര
    0.34
    dimensionality
    0.34
    POSITIVE LOGITS
     скоро
    0.39
    мо
    0.39
     mathsize
    0.38
    謾
    0.38
    поро
    0.37
    ખ
    0.37
     жили
    0.36
    Hai
    0.35
    кси
    0.35
     kaj
    0.34
    Act Density 0.000%

    No Known Activations