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

    Neuronpedia

    INDEX
    Explanations

    creative elements & code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     จึง
    0.48
    ",[],"
    0.41
    "=>$
    0.40
    কমার
    0.40
    拗
    0.39
    নন্দ
    0.39
    、「
    0.38
    ية
    0.38
     所以
    0.38
     おり
    0.38
    POSITIVE LOGITS
     Nights
    0.40
    Yr
    0.39
    Xi
    0.38
     Yr
    0.38
     Vessel
    0.37
     yr
    0.36
     Kirche
    0.36
    MS
    0.36
     nights
    0.36
     κάθε
    0.36
    Act Density 0.000%

    No Known Activations