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

    Neuronpedia

    INDEX
    Explanations

    man, wife, corpses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poiché
    0.41
     whereas
    0.39
     deoarece
    0.39
     wobei
    0.39
     אך
    0.38
     gdyż
    0.38
     pesar
    0.38
     Portanto
    0.38
     있으며
    0.37
     albeit
    0.37
    POSITIVE LOGITS
    …
    0.38
    和服务
    0.34
     —
    0.33
     honestly
    0.33
    ––
    0.32
    ...
    0.32
     Букмекерлар
    0.32
    吧
    0.30
    ….
    0.30
    ━━
    0.29
    Act Density 0.348%

    No Known Activations