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

    Neuronpedia

    INDEX
    Explanations

    Introduce summary or distinction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     negatively
    0.44
     negat
    0.42
     suffix
    0.40
     Hombre
    0.38
     BR
    0.37
     YOUR
    0.36
     insufficiency
    0.35
     ARN
    0.35
    irs
    0.35
     Socks
    0.35
    POSITIVE LOGITS
    जिसे
    0.42
    冲
    0.42
    ای
    0.40
    εν
    0.38
     જેને
    0.38
    GetComponent
    0.37
     сравни
    0.37
    রাদ
    0.37
    ή
    0.36
    да
    0.36
    Act Density 0.001%

    No Known Activations