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

    Neuronpedia

    INDEX
    Explanations

    mode options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    edTest
    0.46
    朢
    0.44
     চৈতন্ত
    0.43
    corpus
    0.42
     型
    0.39
     desember
    0.39
    ą
    0.39
    oa
    0.39
    也好
    0.39
     мозга
    0.38
    POSITIVE LOGITS
     right
    0.47
     UPS
    0.47
     Hebrew
    0.45
     Locator
    0.44
     buzz
    0.44
     Jewish
    0.44
     WiFi
    0.44
     Right
    0.43
     way
    0.43
     unspoken
    0.43
    Act Density 0.000%

    No Known Activations