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

    Neuronpedia

    INDEX
    Explanations

    exert a strong influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oš
    1.76
     berapa
    1.76
    FF
    1.74
    اد
    1.72
    咧
    1.68
    ofthe
    1.68
    Similarity
    1.67
    uck
    1.65
    entingan
    1.65
     localización
    1.64
    POSITIVE LOGITS
     Ahab
    1.70
    ிஸ்த
    1.67
     males
    1.59
     lifetimes
    1.59
    setRequest
    1.48
    ं
    1.48
    нік
    1.44
    বোধ
    1.42
     alienation
    1.40
     قد
    1.40
    Act Density 0.000%

    No Known Activations