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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     secondo
    -0.07
     Springfield
    -0.07
     Але
    -0.06
     Inventory
    -0.06
    \Routing
    -0.06
     Mouth
    -0.06
     سام
    -0.06
     всегда
    -0.06
     Cash
    -0.06
     Jake
    -0.06
    POSITIVE LOGITS
    yen
    0.07
    rons
    0.07
    _classes
    0.07
    issent
    0.06
    isci
    0.06
    容
    0.06
    urous
    0.06
    undler
    0.06
     ชนะ
    0.06
    Sharp
    0.06
    Act Density 0.012%

    No Known Activations