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

    Neuronpedia

    INDEX
    Explanations

    Institutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INAL
    -0.75
    abetes
    -0.67
    pack
    -0.62
    packs
    -0.62
    клопе
    -0.60
    complexContent
    -0.59
    inal
    -0.56
    ital
    -0.55
    hlander
    -0.55
     AssemblyCulture
    -0.53
    POSITIVE LOGITS
    ism
    0.69
    󠁢
    0.55
    isation
    0.54
    izations
    0.50
    izing
    0.49
    ization
    0.48
    led
    0.48
     Association
    0.48
    ized
    0.46
    ize
    0.46
    Act Density 0.050%

    No Known Activations