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

    Neuronpedia

    INDEX
    Explanations

    Contractions and descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.70
    time
    0.56
    size
    0.53
    ipped
    0.52
    tm
    0.52
    tetra
    0.49
    arap
    0.49
    mo
    0.48
    top
    0.48
    multi
    0.48
    POSITIVE LOGITS
    Trades
    0.47
    кает
    0.45
    Descriptions
    0.45
     essays
    0.44
     Gambit
    0.43
    дных
    0.43
     creencias
    0.42
     Sok
    0.42
     headaches
    0.41
    的要求
    0.41
    Act Density 0.005%

    No Known Activations