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

    Neuronpedia

    INDEX
    Explanations

    abstract visual elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حالة
    0.44
    年モデル
    0.40
     stanje
    0.40
    eksiyon
    0.40
     Богу
    0.39
    敛
    0.39
     gyven
    0.38
     情况
    0.38
     స్థితి
    0.37
     спец
    0.37
    POSITIVE LOGITS
     รี
    0.42
     Denison
    0.39
    รี
    0.39
     Sinon
    0.38
    Cornell
    0.38
     Carls
    0.37
     eager
    0.37
    oader
    0.37
    Kir
    0.37
     admirable
    0.37
    Act Density 0.001%

    No Known Activations