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

    Neuronpedia

    INDEX
    Explanations

    adjust their behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contented
    0.50
     premises
    0.49
     proclam
    0.46
    knię
    0.44
    Ⓐ
    0.44
     намере
    0.43
     потра
    0.42
     професси
    0.42
     technicians
    0.42
     prescriptions
    0.42
    POSITIVE LOGITS
    Stere
    0.42
    观众
    0.41
     truk
    0.41
    lou
    0.40
    危机
    0.39
    洊
    0.38
    קו
    0.38
    ራስ
    0.38
    惊喜
    0.38
    Highway
    0.38
    Act Density 0.006%

    No Known Activations