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

    Neuronpedia

    INDEX
    Explanations

    UI text and code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಸರಿಯ
    0.44
     груп
    0.40
     metaphors
    0.39
    cmds
    0.38
    buildSpec
    0.37
    入境
    0.37
    GLAND
    0.37
    ཐ
    0.37
    öpf
    0.36
     grouping
    0.36
    POSITIVE LOGITS
     text
    0.96
    Text
    0.95
    TextView
    0.94
     TextView
    0.93
     Text
    0.93
     UILabel
    0.91
    text
    0.90
     displayText
    0.87
     displaying
    0.87
     display
    0.86
    Act Density 0.026%

    No Known Activations