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

    Neuronpedia

    INDEX
    Explanations

    deez nuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಹಣ
    0.49
    ಕೊ
    0.49
    خی
    0.48
    aku
    0.48
    Punjab
    0.47
    攻撃
    0.47
    হো
    0.47
    linking
    0.46
    埥
    0.46
    ꔹ
    0.46
    POSITIVE LOGITS
    ↵
    0.46
    ,
    0.46
     accolades
    0.42
     igualmente
    0.41
    0.40
     ocean
    0.40
     effluent
    0.40
     throttle
    0.39
     outperform
    0.39
     service
    0.38
    Act Density 0.036%

    No Known Activations