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

    Neuronpedia

    INDEX
    Explanations

    Google Cloud and Firebase services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     campfire
    0.45
     firebase
    0.43
     fireball
    0.43
    Firebase
    0.43
     fireplace
    0.42
    firebase
    0.41
    драт
    0.41
     النار
    0.40
    火
    0.40
    fireplace
    0.39
    POSITIVE LOGITS
    बो
    0.40
    کش
    0.38
    وڑا
    0.37
     broken
    0.35
     vaya
    0.35
    rv
    0.35
     garlic
    0.34
     gå
    0.34
    ้ม
    0.34
     sesuatu
    0.34
    Act Density 0.001%

    No Known Activations