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

    Neuronpedia

    INDEX
    Explanations

    prime number check ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    施設
    0.44
    格納
    0.42
    Me
    0.42
    Changes
    0.42
    変更
    0.42
    ム
    0.41
     മാറ്റ
    0.41
    User
    0.41
    Տ
    0.40
    Eloquent
    0.40
    POSITIVE LOGITS
     inciner
    0.43
     northern
    0.42
    whel
    0.40
     gums
    0.40
     poesía
    0.40
    northern
    0.39
    🖒
    0.38
     War
    0.38
     solitaire
    0.38
     septum
    0.38
    Act Density 0.002%

    No Known Activations