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

    Neuronpedia

    INDEX
    Explanations

    specifying output format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .])
    0.81
    .].
    0.79
    ].)
    0.76
    もあります
    0.76
     connectors
    0.75
     connector
    0.74
     шири
    0.71
     Connector
    0.71
     영향을
    0.70
    ].
    0.69
    POSITIVE LOGITS
     kter
    0.73
    Tourist
    0.72
    يتي
    0.71
    Garage
    0.71
    [*]
    0.71
    Luxury
    0.70
    ※
    0.70
    Greeting
    0.70
    Crack
    0.69
     *:
    0.69
    Act Density 0.000%

    No Known Activations