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

    Neuronpedia

    INDEX
    Explanations

    bang theory, Revolution, ubuntu, Go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.46
    ’
    0.45
     for
    0.42
    )
    0.40
    ០
    0.40
    )$
    0.38
    '
    0.37
    }
    0.37
     pojawi
    0.36
    РА
    0.36
    POSITIVE LOGITS
    os
    0.36
     که
    0.35
    ا
    0.34
    t
    0.34
    á
    0.33
    biotic
    0.32
    mith
    0.32
    ból
    0.32
    مل
    0.31
    går
    0.31
    Act Density 0.092%

    No Known Activations