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

    Neuronpedia

    INDEX
    Explanations

    the first law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    졔
    0.41
     mils
    0.39
    🄴
    0.38
    SequentialGroup
    0.37
    ಿವ
    0.36
     মাথায়
    0.36
    rparam
    0.36
    ႃ
    0.36
     postpaid
    0.35
     așa
    0.35
    POSITIVE LOGITS
    互联网
    0.47
    you
    0.46
     Methods
    0.46
     You
    0.45
     Dan
    0.45
    You
    0.43
    bbs
    0.43
    APPS
    0.42
     Method
    0.42
    OBJ
    0.42
    Act Density 0.000%

    No Known Activations