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

    Neuronpedia

    INDEX
    Explanations

    focus on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.50
    )
    0.47
     in
    0.46
     from
    0.42
    ."
    0.40
    .)
    0.40
     of
    0.39
    ]
    0.39
     on
    0.39
     if
    0.37
    POSITIVE LOGITS
     togetherness
    0.56
     dynamism
    0.54
     idealism
    0.51
     sovereignty
    0.50
     ingenuity
    0.50
     inclusivity
    0.49
     craftsmanship
    0.48
     teknologi
    0.48
     omnichannel
    0.48
     materialism
    0.48
    Act Density 0.212%

    No Known Activations