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

    Neuronpedia

    INDEX
    Explanations

    profession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이유는
    0.43
     probability
    0.43
    然後
    0.42
     odkry
    0.42
    usha
    0.41
    estion
    0.40
    然后
    0.40
     그래서
    0.39
     Probability
    0.39
     然后
    0.39
    POSITIVE LOGITS
     arraigned
    0.38
    rawy
    0.37
     Code
    0.36
    row
    0.34
     Astronomy
    0.34
    COG
    0.34
     App
    0.33
    coded
    0.33
    ActionEvent
    0.33
    фр
    0.33
    Act Density 0.000%

    No Known Activations