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

    Neuronpedia

    INDEX
    Explanations

    implements and utensils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फोटोशूट
    0.46
    云计算
    0.44
    SleepHours
    0.43
    desIP
    0.42
     formData
    0.42
    ciphertext
    0.41
     budgetary
    0.40
    FlaskApp
    0.40
    幄
    0.40
    埧
    0.39
    POSITIVE LOGITS
     spatula
    1.10
     knife
    1.06
     scissors
    0.96
     tongs
    0.95
     tools
    0.94
     knives
    0.93
     trow
    0.93
    工具
    0.87
     spoon
    0.86
     Tools
    0.84
    Act Density 0.047%

    No Known Activations