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

    Neuronpedia

    INDEX
    Explanations

    topic transition phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ismos
    0.49
     இவை
    0.43
     ½
    0.43
    legate
    0.43
     ইহাই
    0.42
     temos
    0.42
    כל
    0.42
    ocop
    0.42
     despicable
    0.42
     dictatorship
    0.40
    POSITIVE LOGITS
     была
    0.44
     était
    0.43
     onscreen
    0.40
     była
    0.40
     omnichannel
    0.39
     ήταν
    0.38
     الفريق
    0.38
     הייתה
    0.38
    ι
    0.38
    ੱ
    0.38
    Act Density 0.005%

    No Known Activations