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

    Neuronpedia

    INDEX
    Explanations

    future actions or recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     further
    1.04
    Further
    0.93
     Further
    0.92
    进一步
    0.89
     дальше
    0.84
    further
    0.80
     dissatisfaction
    0.79
     farther
    0.78
     onward
    0.77
     proceed
    0.77
    POSITIVE LOGITS
    return
    1.23
     return
    1.22
     Return
    1.11
    Return
    1.10
    返回
    1.01
     Returning
    0.99
     returning
    0.99
    returning
    0.98
    Returning
    0.98
     RETURN
    0.97
    Act Density 0.028%

    No Known Activations