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

    Neuronpedia

    INDEX
    Explanations

    claims of high returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    threatening
    0.46
    ப
    0.43
     equate
    0.43
    चार
    0.42
    contamination
    0.42
    𝐼
    0.42
    この
    0.42
    ຜະລິດຕະພັນ
    0.41
     disregarding
    0.41
    such
    0.40
    POSITIVE LOGITS
    MVP
    0.54
     Hub
    0.51
     MVP
    0.49
     Kari
    0.48
     Kone
    0.48
    지는
    0.48
     Faith
    0.46
     MBA
    0.46
     Psalm
    0.46
     Lyft
    0.46
    Act Density 0.001%

    No Known Activations