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

    Neuronpedia

    INDEX
    Explanations

    personal fulfillment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nému
    0.51
    das
    0.46
    dash
    0.44
    dum
    0.44
    stift
    0.44
    light
    0.43
    lys
    0.43
    lyn
    0.42
    naud
    0.41
    herlands
    0.40
    POSITIVE LOGITS
    Ever
    0.44
    и
    0.44
    ῃ
    0.44
    ไปด้วย
    0.44
    ))));
    0.42
    側に
    0.42
    Luxury
    0.42
    ારીખ
    0.42
    案内
    0.41
    ологи
    0.41
    Act Density 0.001%

    No Known Activations