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

    Neuronpedia

    INDEX
    Explanations

    calling superclass methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rower
    0.47
     всех
    0.47
    ্ঠ
    0.47
     alerg
    0.45
     chopper
    0.45
    斯特
    0.44
     வெப்ப
    0.43
     overd
    0.43
     nanow
    0.42
     mouth
    0.42
    POSITIVE LOGITS
    C
    0.48
    integrity
    0.45
    import
    0.44
    a
    0.43
    ה
    0.43
     //</
    0.42
     /**@
    0.41
    \|^
    0.41
    toByteArray
    0.41
    canada
    0.41
    Act Density 0.001%

    No Known Activations