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

    Neuronpedia

    INDEX
    Explanations

    methods starting with `do_`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ksom
    0.44
     tons
    0.43
     lim
    0.40
    HOR
    0.39
    Kp
    0.39
    BRA
    0.38
    ksam
    0.38
    Mang
    0.38
    Kra
    0.38
     mang
    0.38
    POSITIVE LOGITS
     amenity
    0.54
     amenities
    0.45
     SQLAlchemy
    0.44
     டிவி
    0.42
    airbnb
    0.42
     Pillow
    0.41
     Airbnb
    0.40
    बिनेट
    0.40
     Amenities
    0.40
     Gabriel
    0.40
    Act Density 0.000%

    No Known Activations