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

    Neuronpedia

    INDEX
    Explanations

    numbers and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    咦
    0.44
     अटे
    0.42
    hány
    0.39
    就行
    0.39
     squamous
    0.38
    raccoon
    0.37
    mAb
    0.37
    🦳
    0.37
     −/−
    0.37
     powdery
    0.37
    POSITIVE LOGITS
    cean
    0.41
    カ
    0.40
    0
    0.38
     Odds
    0.35
    ட்ட
    0.35
     শুদ্ধ
    0.34
     comforts
    0.34
    ρφ
    0.33
    kada
    0.33
    ಣೆ
    0.32
    Act Density 0.009%

    No Known Activations