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

    Neuronpedia

    INDEX
    Explanations

    dependency injection lifetimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preso
    -0.94
     Crear
    -0.85
    breviations
    -0.84
    relevant
    -0.82
    assured
    -0.82
    下一步
    -0.82
    頜
    -0.82
     grâce
    -0.81
    ῆς
    -0.80
    žiť
    -0.80
    POSITIVE LOGITS
    Singleton
    1.18
    Transient
    1.16
    Scoped
    1.14
     Singleton
    1.01
     services
    0.99
     transient
    0.98
     Sco
    0.90
     Transient
    0.85
     singleton
    0.85
    services
    0.84
    Act Density 0.005%

    No Known Activations