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

    Neuronpedia

    INDEX
    Explanations

    issues relevantwould seem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    甜
    0.52
    涉及到
    0.51
    cum
    0.42
    attiyam
    0.41
    га
    0.41
    涉及
    0.40
    FindingsRequest
    0.40
    摫
    0.40
    lastCursor
    0.39
    ку
    0.38
    POSITIVE LOGITS
     Jodie
    0.48
     poster
    0.45
     bladder
    0.44
     endot
    0.44
     Vodafone
    0.44
     GDP
    0.43
     BNB
    0.43
     ankle
    0.43
     comedians
    0.42
    Seems
    0.42
    Act Density 0.004%

    No Known Activations