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

    Neuronpedia

    INDEX
    Explanations

    in order to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queries
    0.45
     analysing
    0.45
     Queries
    0.45
     achieving
    0.44
     overcoming
    0.42
     acquiring
    0.41
     optimality
    0.40
     informatics
    0.40
     Dimension
    0.40
     appli
    0.40
    POSITIVE LOGITS
    更好地
    0.49
     thereby
    0.47
    从而
    0.44
     facilitate
    0.41
    보다
    0.41
     Thereby
    0.41
     BETTER
    0.40
     horribly
    0.39
    进而
    0.39
    更好的
    0.39
    Act Density 0.002%

    No Known Activations