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

    Neuronpedia

    INDEX
    Explanations

    being novel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を示
    0.39
     pintu
    0.39
    뗑
    0.39
     வளர்ச்சி
    0.39
    死的
    0.39
    garia
    0.39
     बदली
    0.39
     Advancement
    0.38
     غلط
    0.38
     SPDX
    0.38
    POSITIVE LOGITS
    akup
    0.43
    介入
    0.42
    ALK
    0.41
     positive
    0.40
    ज़्
    0.37
    yst
    0.37
    Ǘ
    0.36
    各
    0.36
     Brunner
    0.35
     BURE
    0.35
    Act Density 0.000%

    No Known Activations