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

    Neuronpedia

    INDEX
    Explanations

    instructing tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ópt
    0.38
    bz
    0.38
    érez
    0.38
    iteit
    0.38
    ñez
    0.38
     parque
    0.37
     Parque
    0.37
    입니다
    0.37
    éz
    0.37
    斋
    0.37
    POSITIVE LOGITS
    '>";
    0.38
    伝説
    0.37
    鯽
    0.36
     、,
    0.35
     INKA
    0.35
     Balancing
    0.34
    셨
    0.34
    ',[
    0.34
     मच्छ
    0.34
     sajana
    0.33
    Act Density 0.004%

    No Known Activations