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

    Neuronpedia

    INDEX
    Explanations

    code generation requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     println
    0.45
     trivially
    0.45
     computes
    0.44
     monotonically
    0.44
     evaluates
    0.44
     άλλ
    0.44
     =~
    0.43
     mung
    0.42
     nominally
    0.42
     বেশী
    0.42
    POSITIVE LOGITS
    Integration
    0.57
    Integrated
    0.56
    Integrating
    0.54
    integrated
    0.53
     integration
    0.51
    coating
    0.49
     Integration
    0.49
    integration
    0.48
    implementation
    0.48
    詳細
    0.48
    Act Density 0.024%

    No Known Activations