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

    Neuronpedia

    INDEX
    Explanations

    lists with options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CLASS
    0.31
    TYPE
    0.30
    click
    0.29
    ollowing
    0.29
    Based
    0.29
    FILES
    0.29
    Following
    0.28
    兩個
    0.28
    does
    0.27
    Class
    0.27
    POSITIVE LOGITS
     communists
    0.31
    लखनऊ
    0.29
     séjour
    0.29
     disregarded
    0.28
     devout
    0.28
     thwarted
    0.28
    ﺀ
    0.28
    0.28
    甃
    0.28
    Ნ
    0.28
    Act Density 0.043%

    No Known Activations