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

    Neuronpedia

    INDEX
    Explanations

    Serve immediately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Suppose
    1.13
     उर्वर
    1.10
    ால
    1.10
     RequestMethod
    1.09
    asmuch
    1.04
    ة
    1.04
    辙
    1.03
     assertFalse
    1.02
     AudioClip
    1.02
     Suppose
    1.01
    POSITIVE LOGITS
    ്യം
    1.00
     rote
    0.95
     alla
    0.95
    yclerView
    0.92
     Keb
    0.92
    нент
    0.92
    至于
    0.92
    ும்
    0.91
    dropDown
    0.91
    NG
    0.90
    Act Density 0.005%

    No Known Activations