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

    Neuronpedia

    INDEX
    Explanations

    lists and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    0.43
     capable
    0.41
     encouraging
    0.41
    ourage
    0.40
    of
    0.40
     impact
    0.40
     willingness
    0.38
     endroits
    0.38
     अपनी
    0.38
    想要
    0.38
    POSITIVE LOGITS
     هناك
    0.63
     iar
    0.59
     there
    0.57
    มีการ
    0.53
    there
    0.52
     houve
    0.52
     나머
    0.50
     मुश्किलें
    0.50
     nové
    0.49
    There
    0.49
    Act Density 0.191%

    No Known Activations