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

    Neuronpedia

    INDEX
    Explanations

    S&P 500

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceans
    0.45
    sa
    0.43
    7
    0.42
    tsv
    0.42
    ANG
    0.42
    6
    0.42
    lz
    0.40
    nich
    0.40
    xlsx
    0.40
    tbx
    0.39
    POSITIVE LOGITS
    ’
    0.55
    '
    0.53
     ecosystem
    0.48
     pharmac
    0.48
     customization
    0.47
     estilos
    0.47
     opcao
    0.46
     leafy
    0.46
     assets
    0.46
     organizations
    0.46
    Act Density 0.004%

    No Known Activations