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

    Neuronpedia

    INDEX
    Explanations

    instructions, explanations, details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ibi
    0.52
    欧美
    0.46
     in
    0.46
     Buzz
    0.44
    1
    0.44
     옆
    0.44
     Definitions
    0.43
    MessageBox
    0.43
     Discipl
    0.42
    0
    0.42
    POSITIVE LOGITS
     поступ
    0.54
     thrombo
    0.52
     влия
    0.49
     полномо
    0.49
     xw
    0.48
    𝘢
    0.48
     thawing
    0.47
     gleaming
    0.46
     শিকার
    0.46
    。(
    0.46
    Act Density 0.000%

    No Known Activations