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

    Neuronpedia

    INDEX
    Explanations

    conversational acknowledgements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jurul
    0.72
    围绕
    0.67
    собенности
    0.66
     inoltre
    0.66
     కలిగి
    0.65
     사용하여
    0.65
    以下の
    0.64
     gồm
    0.63
    ēs
    0.63
    떤
    0.62
    POSITIVE LOGITS
     Admittedly
    2.13
     yeah
    2.11
     Obviously
    2.05
     admittedly
    2.04
     Seriously
    2.00
     Yeah
    1.98
     yep
    1.91
    Seriously
    1.88
     Needless
    1.87
     Ironically
    1.87
    Act Density 0.968%

    No Known Activations