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

    Neuronpedia

    INDEX
    Explanations

    -ly followed by positive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल्पन
    0.43
    usely
    0.43
     virtualization
    0.42
     Kiran
    0.41
     듯
    0.40
     Bibliography
    0.39
    듯
    0.39
    हाला
    0.39
    fontsize
    0.38
    kowo
    0.38
    POSITIVE LOGITS
     hablando
    0.70
     falando
    0.61
     driven
    0.61
     oriented
    0.60
     significant
    0.58
     relevant
    0.57
    speaking
    0.56
     savvy
    0.54
     speaking
    0.54
     astute
    0.54
    Act Density 0.030%

    No Known Activations