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

    Neuronpedia

    INDEX
    Explanations

    example, followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㖪
    0.45
    obac
    0.43
    vam
    0.43
    coid
    0.41
    jskiego
    0.41
    osw
    0.40
     varie
    0.40
    res
    0.40
    ροσ
    0.40
    ăl
    0.40
    POSITIVE LOGITS
     Maximum
    0.41
     sentiment
    0.41
    どの
    0.41
     would
    0.41
     training
    0.40
     hope
    0.40
     Engel
    0.40
     pith
    0.40
     can
    0.39
     Yani
    0.39
    Act Density 0.001%

    No Known Activations