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

    Neuronpedia

    INDEX
    Explanations

    wet, damp, soaked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    绚
    0.42
     تقس
    0.38
    荚
    0.38
    傆
    0.37
    ҕ
    0.37
    ⏸
    0.37
    栾
    0.37
     deleting
    0.37
    زيز
    0.37
    லான
    0.37
    POSITIVE LOGITS
     wet
    2.77
     damp
    2.69
    Wet
    2.45
     soaked
    2.41
     Wet
    2.38
    wet
    2.38
    湿
    2.28
     Damp
    2.16
     drenched
    2.13
     dampened
    2.09
    Act Density 0.051%

    No Known Activations