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

    Neuronpedia

    INDEX
    Explanations

    He returns or helps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igel
    -0.10
    {:
    -0.09
    ,void
    -0.09
    ertia
    -0.08
    igin
    -0.08
    awns
    -0.08
    æģ¯
    -0.08
     craft
    -0.08
    ansa
    -0.08
    íĬ
    -0.08
    POSITIVE LOGITS
     last
    0.12
     said
    0.12
    miss
    0.10
     clock
    0.10
     will
    0.10
     jet
    0.10
     –;
    0.09
     Join
    0.09
     joins
    0.09
    ¿
    0.09
    Act Density 0.078%

    No Known Activations