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

    Neuronpedia

    INDEX
    Explanations

    advice for yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    0.48
     {})
    0.44
    )"
    0.43
    )</
    0.43
     was
    0.43
    RAchievement
    0.43
    )}}
    0.42
     Darstellung
    0.42
     LGBTQ
    0.42
     magie
    0.41
    POSITIVE LOGITS
     yourself
    0.68
    yourself
    0.64
     نفسك
    0.57
     yourselves
    0.51
    on
    0.48
     Yourself
    0.47
    especially
    0.47
    те
    0.44
    𝐞
    0.43
    ø
    0.43
    Act Density 1.163%

    No Known Activations