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

    Neuronpedia

    INDEX
    Explanations

    asking for a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secretos
    0.82
     problemat
    0.63
     expon
    0.62
    .
    0.61
     rumores
    0.60
     asuntos
    0.59
     inder
    0.58
    ことを
    0.57
     on
    0.57
     предпо
    0.56
    POSITIVE LOGITS
    description
    1.20
     description
    1.16
    describe
    1.16
     описы
    1.14
    Description
    1.09
     descriptions
    1.09
    描述
    1.09
     describes
    1.08
    Describe
    1.07
     describe
    1.05
    Act Density 0.196%

    No Known Activations