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

    Neuronpedia

    INDEX
    Explanations

    translating color expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عدالت
    0.48
    Inspection
    0.47
    Methoxy
    0.45
     wort
    0.44
     stumpage
    0.44
    Carlton
    0.44
    Downtown
    0.43
    لس
    0.43
    Rent
    0.43
    Mild
    0.43
    POSITIVE LOGITS
    to
    0.57
    label
    0.54
    create
    0.52
     不需要
    0.51
    無需
    0.50
    bi
    0.50
    use
    0.49
    vectors
    0.49
    group
    0.48
    beta
    0.47
    Act Density 0.001%

    No Known Activations