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

    Neuronpedia

    INDEX
    Explanations

    locations and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     средства
    0.38
    yacute
    0.37
     स्टेशन
    0.37
    芍
    0.37
    的用户
    0.37
     tache
    0.37
     SME
    0.36
    须知
    0.36
    工业
    0.36
     Sval
    0.36
    POSITIVE LOGITS
    LOW
    0.41
    лис
    0.40
    ވެ
    0.40
    लोड
    0.39
    Ს
    0.39
    rechts
    0.39
    吿
    0.38
    निष्
    0.38
     hz
    0.37
     HA
    0.36
    Act Density 0.001%

    No Known Activations