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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BleStatus
    0.29
    RELATIVA
    0.27
    UnderWater
    0.27
     言っ
    0.27
    ammens
    0.26
    positroid
    0.26
    hydrocèle
    0.25
    vvvert
    0.25
    jelder
    0.25
     רק
    0.25
    POSITIVE LOGITS
     P
    0.26
    ’
    0.26
             
    0.25
    P
    0.24
    <0xE2>
    0.23
    i
    0.22
     l
    0.22
    ”
    0.22
    -
    0.21
    ↵
    0.21
    Act Density 0.148%

    No Known Activations