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

    Neuronpedia

    INDEX
    Explanations

    Google container registries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cột
    0.40
     alpine
    0.40
    ('-
    0.39
    ้อน
    0.38
     lod
    0.38
     Alpine
    0.38
     ALPINE
    0.38
     REST
    0.37
    茣
    0.37
     cellulose
    0.36
    POSITIVE LOGITS
     Harbor
    0.53
     harbor
    0.51
     harbors
    0.51
     harbour
    0.45
     quay
    0.44
     Quay
    0.44
     Container
    0.44
    Container
    0.43
     Emissions
    0.42
     harbours
    0.42
    Act Density 0.007%

    No Known Activations