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

    Neuronpedia

    INDEX
    Explanations

    descriptive or conditional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RES
    0.55
    خ
    0.53
    苏
    0.50
    Mat
    0.50
    MAT
    0.49
    ються
    0.49
    лів
    0.47
    KIS
    0.46
    （
    0.46
    зло
    0.45
    POSITIVE LOGITS
     habilit
    0.59
     شويه
    0.47
     미래
    0.46
     갤럭시
    0.46
     살펴보
    0.45
    시키는
    0.45
    ConnectionType
    0.45
    ေး
    0.45
    gan
    0.44
     회원
    0.44
    Act Density 0.000%

    No Known Activations