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

    Neuronpedia

    INDEX
    Explanations

    names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appe
    0.21
     mortals
    0.20
     proses
    0.20
     grotesque
    0.19
     monstrous
    0.19
     deceit
    0.19
     enlightenment
    0.19
     barbaric
    0.19
     powdery
    0.18
     defin
    0.18
    POSITIVE LOGITS
    м
    0.23
    й
    0.23
    к
    0.23
    а
    0.23
    ла
    0.23
     родился
    0.22
    е
    0.22
    з
    0.22
    р
    0.21
    ня
    0.21
    Act Density 0.026%

    No Known Activations