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

    Neuronpedia

    INDEX
    Explanations

    short haired tabby, bits, Robb, prescriptions, Quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    高志森
    0.58
    ेंस
    0.53
     Серге
    0.52
    мы
    0.50
     улице
    0.50
    েক্টর
    0.49
    bsen
    0.48
    шибка
    0.48
    ༦
    0.48
    财经
    0.48
    POSITIVE LOGITS
     prototype
    0.45
     überw
    0.44
    T
    0.44
     Walk
    0.40
    St
    0.38
     prototypes
    0.38
    Walk
    0.38
     St
    0.37
     Lincoln
    0.37
    0.37
    Act Density 0.002%

    No Known Activations