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

    Neuronpedia

    INDEX
    Explanations

    raise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discrepancy
    -0.07
    FTER
    -0.07
     streak
    -0.07
    тивного
    -0.07
    ptom
    -0.07
    ({...
    -0.06
    อด
    -0.06
     slipping
    -0.06
     disappear
    -0.06
     Kol
    -0.06
    POSITIVE LOGITS
     Raise
    0.09
     raises
    0.09
     raised
    0.09
     raise
    0.09
     raising
    0.09
    Raises
    0.07
     Raised
    0.07
     جع
    0.07
     Farmers
    0.07
    .SO
    0.07
    Act Density 0.012%

    No Known Activations