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

    Neuronpedia

    INDEX
    Explanations

    command line arguments like `/target`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GPI
    0.42
    APR
    0.38
    0.37
     GPI
    0.37
     DEN
    0.36
     जींस
    0.36
     tempted
    0.36
     epiph
    0.36
    perplexity
    0.36
     deng
    0.35
    POSITIVE LOGITS
     /ˈ
    0.48
     console
    0.47
     Generate
    0.44
    ","/
    0.44
     Console
    0.43
     /
    0.41
    Generate
    0.41
     /,
    0.40
    generate
    0.40
     /=
    0.40
    Act Density 0.006%

    No Known Activations